Tootfinder

The Hidden Cost of Correlation: Rethinking Privacy Leakage in Local Differential Privacy
Sandaru Jayawardana, Sennur Ulukus, Ming Ding, Kanchana Thilakarathna
https://arxiv.org/abs/2508.12539

The Hidden Cost of Correlation: Rethinking Privacy Leakage in Local Differential Privacy
Local differential privacy (LDP) has emerged as a promising paradigm for privacy-preserving data collection in distributed systems, where users contribute multi-dimensional records with potentially correlated attributes. Recent work has highlighted that correlation-induced privacy leakage (CPL) plays a critical role in shaping the privacy-utility trade-off under LDP, especially when correlations exist among attributes. Nevertheless, it remains unclear to what extent the prevailing assumptions a…

I agree, really think twice or just don't... Also think about US government accessing your personal data if they want....
https://techcrunch.com/2025/07/19/for-privacy-and-security-think-twice-before-granting-ai-acces…

For privacy and security, think twice before granting AI access to your personal data | TechCrunch
AI chatbots, assistants and agents are increasingly asking for gross levels of access to your personal data under the guise of needing your information to make them work.

Google will pay $30M to settle a class action lawsuit alleging it violated kids' privacy on YouTube by collecting data without parental consent for targeted ads (Jonathan Stempel/Reuters)
https://www.reuters.com/sustainability/boa

Can I Trust This Chatbot? Assessing User Privacy in AI-Healthcare Chatbot Applications
Ramazan Yener, Guan-Hung Chen, Ece Gumusel, Masooda Bashir
https://arxiv.org/abs/2509.14581

Can I Trust This Chatbot? Assessing User Privacy in AI-Healthcare Chatbot Applications
As Conversational Artificial Intelligence (AI) becomes more integrated into everyday life, AI-powered chatbot mobile applications are increasingly adopted across industries, particularly in the healthcare domain. These chatbots offer accessible and 24/7 support, yet their collection and processing of sensitive health data present critical privacy concerns. While prior research has examined chatbot security, privacy issues specific to AI healthcare chatbots have received limited attention. Our s…

Shut them down. Easy question
https://infosec.exchange/@steelefortress/115062158543467536

Distributed Batch Matrix Multiplication: Trade-Offs in Download Rate, Randomness, and Privacy
Amirhosein Morteza, Remi A. Chou
https://arxiv.org/abs/2509.15047 https://

Distributed Batch Matrix Multiplication: Trade-Offs in Download Rate, Randomness, and Privacy
We study the trade-off between communication rate and privacy for distributed batch matrix multiplication of two independent sequences of matrices $\bold{A}$ and $\bold{B}$ with uniformly distributed entries. In our setting, $\bold{B}$ is publicly accessible by all the servers while $\bold{A}$ must remain private. A user is interested in evaluating the product $\bold{AB}$ with the responses from the $k$ fastest servers. For a given parameter $α\in [0, 1]$, our privacy constraint must ensure th…

Google will pay $30M to settle a class action lawsuit alleging it violated kids' privacy on YouTube by collecting data without parental consent for targeted ads (Jonathan Stempel/Reuters)
https://www.reuters.com/sustainability/boa

Beyond Data Privacy: New Privacy Risks for Large Language Models
Yuntao Du, Zitao Li, Ninghui Li, Bolin Ding
https://arxiv.org/abs/2509.14278 https://arxiv…

Beyond Data Privacy: New Privacy Risks for Large Language Models
Large Language Models (LLMs) have achieved remarkable progress in natural language understanding, reasoning, and autonomous decision-making. However, these advancements have also come with significant privacy concerns. While significant research has focused on mitigating the data privacy risks of LLMs during various stages of model training, less attention has been paid to new threats emerging from their deployment. The integration of LLMs into widely used applications and the weaponization of …

Protect your privacy – Start now with Signal
 
Autocracies always implement broad surveillance methods in order to identify and punish resistance. Surveillance can take many forms including the capture of your social media posts and email, monitoring your connections to web sites, and preventing the use of private communications through encryption back-doors and other means.
 
Take action now to create ways to communicate privately with your family, friends and colleague…

Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
Bihao Zhan, Jie Zhou, Junsong Li, Yutao Yang, Shilian Chen, Qianjun Pan, Xin Li, Wen Wu, Xingjiao Wu, Qin Chen, Hang Yan, Liang He
https://arxiv.org/abs/2509.12958

Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. Traditional privacy methods, like a uniform Differential Privacy (DP) budget, indiscriminately protect all data, leading to substantial model utility degradation and hindering CL deployment in privacy-sensitive areas. To overcome this, we propose a privacy-enhanced continual learning (PeCL) framework that forgets what'…

Highlights from FPF’s July 2025 Technologist Roundtable: AI Unlearning and Technical Guardrails
https://fpf.org/blog/highlights-from-fpfs-july-2025-technologist-roundtable-ai-unlearning-and-technical-guardrails/

Watchdog finds MrBeast improperly collected children’s data https://therecord.media/watchdog-mrbeast-youtube-privacy-colection

ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learning
Zihou Wu (School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China), Yuecheng Li (School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China), Tianchi Liao (School of Software Engineering, Sun Yat-sen University, Zhuhai, China), Jian Lou (School of Software Engineering, Sun Yat-sen University, Zhuhai, China), Chuan Chen (School of Computer Science and E…

ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learning
Federated learning (FL) faces a critical dilemma: existing protection mechanisms like differential privacy (DP) and homomorphic encryption (HE) enforce a rigid trade-off, forcing a choice between model utility and computational efficiency. This lack of flexibility hinders the practical implementation. To address this, we introduce ParaAegis, a parallel protection framework designed to give practitioners flexible control over the privacy-utility-efficiency balance. Our core innovation is a strat…

The EU (still) wants to scan
your private messages and photos
it’s not too late to act:
Reach out to your Representatives.
#chatcontrol #privacy #CSAM

Swiss government looks to undercut privacy tech, stoking fears of mass surveillance
The Swiss government could soon require service providers with more than 5,000 users to collect government-issued identification, retain subscriber data for six months and, in many cases, disable encryption.
🇨🇭 https://

Swiss government looks to undercut privacy tech, stoking fears of mass surveillance
Swiss-based providers of secure email, VPNs and other digital services say a pending government proposal would be catastrophic to their ability to protect the privacy of users.

Training-free Dimensionality Reduction via Feature Truncation: Enhancing Efficiency in Privacy-preserving Multi-Biometric Systems
Florian Bayer, Maximilian Russo, Christian Rathgeb
https://arxiv.org/abs/2508.11419

Training-free Dimensionality Reduction via Feature Truncation: Enhancing Efficiency in Privacy-preserving Multi-Biometric Systems
Biometric recognition is widely used, making the privacy and security of extracted templates a critical concern. Biometric Template Protection schemes, especially those utilizing Homomorphic Encryption, introduce significant computational challenges due to increased workload. Recent advances in deep neural networks have enabled state-of-the-art feature extraction for face, fingerprint, and iris modalities. The ubiquity and affordability of biometric sensors further facilitate multi-modal fusion…

AI For Privacy in Smart Homes: Exploring How Leveraging AI-Powered Smart Devices Enhances Privacy Protection
Wael Albayaydh, Ivan Flechais, Rui Zhao, Jood Albayaydh
https://arxiv.org/abs/2509.14050

AI For Privacy in Smart Homes: Exploring How Leveraging AI-Powered Smart Devices Enhances Privacy Protection
Privacy concerns and fears of unauthorized access in smart home devices often stem from misunderstandings about how data is collected, used, and protected. This study explores how AI-powered tools can offer innovative privacy protections through clear, personalized, and contextual support to users. Through 23 in-depth interviews with users, AI developers, designers, and regulators, and using Grounded Theory analysis, we identified two key themes: Aspirations for AI-Enhanced Privacy - how users …

Source identifiers are used to track your activity on a site:
Where you came from, what device you use, and even who you talk to.
Whether it's written clearly in the url or tied to a random string of characters, it's assigned to your activity.
When you send a link containing a source identifier to somebody and they click it, it signals to the website that you two are connected.
And that data goes right back to the website operators, and thus their advertisers…

For EU peeps: The EU (still) wants to scan
your private messages and photos https://fightchatcontrol.eu/

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
Vaidehi Patil, Elias Stengel-Eskin, Mohit Bansal
https://arxiv.org/abs/2509.14284

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
As large language models (LLMs) become integral to multi-agent systems, new privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations. In particular, seemingly innocuous responses, when composed across interactions, can cumulatively enable adversaries to recover sensitive information, a phenomenon we term compositional privacy leakage. We present the first systematic study of such compositional privacy leaks and possible mitigation methods in multi-agent…

A Large-Scale Web Search Dataset for Federated Online Learning to Rank
Marcel Gregoriadis, Jingwei Kang, Johan Pouwelse
https://arxiv.org/abs/2508.12353 https://

A Large-Scale Web Search Dataset for Federated Online Learning to Rank
The centralized collection of search interaction logs for training ranking models raises significant privacy concerns. Federated Online Learning to Rank (FOLTR) offers a privacy-preserving alternative by enabling collaborative model training without sharing raw user data. However, benchmarks in FOLTR are largely based on random partitioning of classical learning-to-rank datasets, simulated user clicks, and the assumption of synchronous client participation. This oversimplifies real-world dynami…

Hang on. Is it me or the buttons to change privacy and language changed places on the webby mastodon?

When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing
Mahdi Dhaini, Stephen Meisenbacher, Ege Erdogan, Florian Matthes, Gjergji Kasneci
https://arxiv.org/abs/2508.10482

When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing
In the study of trustworthy Natural Language Processing (NLP), a number of important research fields have emerged, including that of \textit{explainability} and \textit{privacy}. While research interest in both explainable and privacy-preserving NLP has increased considerably in recent years, there remains a lack of investigation at the intersection of the two. This leaves a considerable gap in understanding of whether achieving \textit{both} explainability and privacy is possible, or whether t…

Is there a free, privacy friendly AI like duck.ai from #duckduckgo that can create images? No registration, just using it?
#ai #imagecreation

Watching the second to last season of SVU (wifey loves it) and the cops just got info from being in a Discord server. Realistic. The FBI are all over Discord too. Always keep that in mind. Say nothing sensitive there. Discord servers are NOT secure, the authorities can always easily get in, and they often do.
#Discord #privacy

Yes, I use #Monero, almost daily!
But today, I decided to spin up a fresh wallet, feel free to support me, or spoil me a bit for my birthday this Friday, August, 22.
84PZaY3aMkVWKr8164cj5mEA7y3JsSwezbc1uSiSiZRkeqCLYWbi6GgSxoY8GyEa6r9kwPk583JR2PpxPHmqZpCgE7g4CyK
Unlike the hype coins, surveillance “crypto,” scams, government-controlled money, Monero is built on real privacy, r…

Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes
Zhou Feng, Jiahao Chen, Chunyi Zhou, Yuwen Pu, Qingming Li, Tianyu Du, Shouling Ji
https://arxiv.org/abs/2507.12932

Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes
The rapid advancement of voice deepfake technologies has raised serious concerns about user audio privacy, as attackers increasingly exploit publicly available voice data to generate convincing fake audio for malicious purposes such as identity theft, financial fraud, and misinformation campaigns. While existing defense methods offer partial protection, they face critical limitations, including weak adaptability to unseen user data, poor scalability to long audio, rigid reliance on white-box kn…

Privacy-Preserving Fusion for Multi-Sensor Systems Under Multiple Packet Dropouts
Jie Huang, Jason J. R. Liu
https://arxiv.org/abs/2507.13286 https://

Privacy-Preserving Fusion for Multi-Sensor Systems Under Multiple Packet Dropouts
Wireless sensor networks (WSNs) are critical components in modern cyber-physical systems, enabling efficient data collection and fusion through spatially distributed sensors. However, the inherent risks of eavesdropping and packet dropouts in such networks pose significant challenges to secure state estimation. In this paper, we address the privacy-preserving fusion estimation (PPFE) problem for multi-sensor systems under multiple packet dropouts and eavesdropping attacks. To mitigate these iss…

This is a spectacular way to get folks to see the impact of the #surveillance state. Great job #MassiveAttack!
#privacy

Massive Attack Turns Concert Into Facial Recognition Surveillance Experiment
Massive Attack used live facial recognition technology on concertgoers, turning surveillance into provocative art that sparked debate about privacy.

SynBench: A Benchmark for Differentially Private Text Generation
Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar, Iqra Zahid, Yuping Wu, Yulong Wu, Hao Li, Jie Zhang, Warren Del-Pinto, Goran Nenadic, Siew Kei Lam, Anil Anthony Bharath
https://arxiv.org/abs/2509.14594

SynBench: A Benchmark for Differentially Private Text Generation
Data-driven decision support in high-stakes domains like healthcare and finance faces significant barriers to data sharing due to regulatory, institutional, and privacy concerns. While recent generative AI models, such as large language models, have shown impressive performance in open-domain tasks, their adoption in sensitive environments remains limited by unpredictable behaviors and insufficient privacy-preserving datasets for benchmarking. Existing anonymization methods are often inadequate…

On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions
Daniel M. Jimenez-Gutierrez, Yelizaveta Falkouskaya, Jose L. Hernandez-Ramos, Aris Anagnostopoulos, Ioannis Chatzigiannakis, Andrea Vitaletti
https://arxiv.org/abs/2508.13730

On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions
Federated Learning (FL) is an emerging distributed machine learning paradigm enabling multiple clients to train a global model collaboratively without sharing their raw data. While FL enhances data privacy by design, it remains vulnerable to various security and privacy threats. This survey provides a comprehensive overview of more than 200 papers regarding the state-of-the-art attacks and defense mechanisms developed to address these challenges, categorizing them into security-enhancing and pr…

SENSOR: An ML-Enhanced Online Annotation Tool to Uncover Privacy Concerns from User Reviews in Social-Media Applications
Labiba Farah, Mohammad Ridwan Kabir, Shohel Ahmed, MD Mohaymen Ul Anam, Md. Sakibul Islam
https://arxiv.org/abs/2507.10640

SENSOR: An ML-Enhanced Online Annotation Tool to Uncover Privacy Concerns from User Reviews in Social-Media Applications
The widespread use of social media applications has raised significant privacy concerns, often highlighted in user reviews. These reviews also provide developers with valuable insights into improving apps by addressing issues and introducing better features. However, the sheer volume and nuanced nature of reviews make manual identification and prioritization of privacy-related concerns challenging for developers. Previous studies have developed software utilities to automatically classify user …

This feels like a never ending fight 😩
And it’s so transparent, no more privacy for thee*
*unless you’re an EU politician 🙃
#Privacy

To do for Linkedin users.

Wer noch nicht weiß, was ein überspezifisches Dementi ist, findet hier ein schönes Beispiel:
2015 enthüllte etwa die NGO Privacy International, dass Pakistan Überwachungstechnologien deutscher Unternehmen nutzte. Bereits damals war die massive Überwachungswut des Landes bekannt. Eines der deutschen Unternehmen, Utimaco, soll Medienberichten zufolge auch in Myanmar aktiv gewesen sein. Auf Anfrage hieß es von Utimaco, das Unternehmen habe stets alle Gesetze und Vorschriften e…

Switzerland proposes regulations forcing service providers to collect user IDs and disable encryption, threatening its status as a haven for privacy tech firms (Suzanne Smalley/The Record)
https://therecord.media/switzerland-digital-privacy-law-proton-priv…

Swiss government looks to undercut privacy tech, stoking fears of mass surveillance
Switzerland-based providers of secure email, VPNs and other digital services say a pending government proposal would be catastrophic to their ability to protect the privacy of users.

Smooth Flow Matching
Jianbin Tan, Anru R. Zhang
https://arxiv.org/abs/2508.13831 https://arxiv.org/pdf/2508.13831…

Smooth Flow Matching
Functional data, i.e., smooth random functions observed over a continuous domain, are increasingly available in areas such as biomedical research, health informatics, and epidemiology. However, effective statistical analysis for functional data is often hindered by challenges such as privacy constraints, sparse and irregular sampling, infinite dimensionality, and non-Gaussian structures. To address these challenges, we introduce a novel framework named Smooth Flow Matching (SFM), tailored for g…

Why are so many people still afraid of losing their power even though they have no (relevant) power? In other words, decentralized Internet and its advantage, if implemented accordingly, is as positive for privacy as business secrets. Yes, there are always some crazy people who exploit this for their perversity and politics, but you can catch them even if they are properly investigated ~ #MindNode…

Exploring User Security and Privacy Attitudes and Concerns Toward the Use of General-Purpose LLM Chatbots for Mental Health
Jabari Kwesi, Jiaxun Cao, Riya Manchanda, Pardis Emami-Naeini
https://arxiv.org/abs/2507.10695

Exploring User Security and Privacy Attitudes and Concerns Toward the Use of General-Purpose LLM Chatbots for Mental Health
Individuals are increasingly relying on large language model (LLM)-enabled conversational agents for emotional support. While prior research has examined privacy and security issues in chatbots specifically designed for mental health purposes, these chatbots are overwhelmingly "rule-based" offerings that do not leverage generative AI. Little empirical research currently measures users' privacy and security concerns, attitudes, and expectations when using general-purpose LLM-enabled chatbots to …

Spotify Privacy Quick Guide (Asking for a Friend) https://musictechpolicy.com/2025/09/06/spotify-privacy-quick-guide-asking-for-a-friend/

Spotify Privacy Quick Guide (Asking for a Friend)
Spotify’s defaults trade convenience for exposure. This quick guide explains what Spotify collects, why recent policy changes matter, and the specific settings that curb public-by-default leaks, ad…

Crosslisted article(s) found for cs.DC. https://arxiv.org/list/cs.DC/new
[1/1]:
- AegisBlock: A Privacy-Preserving Medical Research Framework using Blockchain
Calkin Garg, Omar Rios Cruz, Tessa Andersen, Gaby G. Dagher, Donald Winiecki, Min Long

Optimizing Region of Interest Selection for Effective Embedding in Video Steganography Based on Genetic Algorithms
Nizheen A. Ali, Ramadhan J. Mstafa
https://arxiv.org/abs/2508.13710

Optimizing Region of Interest Selection for Effective Embedding in Video Steganography Based on Genetic Algorithms
With the widespread use of the internet, there is an increasing need to ensure the security and privacy of transmitted data. This has led to an intensified focus on the study of video steganography, which is a technique that hides data within a video cover to avoid detection. The effectiveness of any steganography method depends on its ability to embed data without altering the original video quality while maintaining high efficiency. This paper proposes a new method to video steganography, whi…

Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
Jinyu Lu, Xinrong Sun, Yunting Tao, Tong Ji, Fanyu Kong, Guoqiang Yang
https://arxiv.org/abs/2508.12832

Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
The widespread adoption of convolutional neural networks (CNNs) in resource-constrained scenarios has driven the development of Machine Learning as a Service (MLaaS) system. However, this approach is susceptible to privacy leakage, as the data sent from the client to the untrusted cloud server often contains sensitive information. Existing CNN privacy-preserving schemes, while effective in ensuring data confidentiality through homomorphic encryption and secret sharing, face efficiency bottlenec…

Crosslisted article(s) found for cs.IT. https://arxiv.org/list/cs.IT/new
[1/1]:
- The Hidden Cost of Correlation: Rethinking Privacy Leakage in Local Differential Privacy
Sandaru Jayawardana, Sennur Ulukus, Ming Ding, Kanchana Thilakarathna

PP-STAT: An Efficient Privacy-Preserving Statistical Analysis Framework using Homomorphic Encryption
Hyunmin Choi
https://arxiv.org/abs/2508.12093 https://…

PP-STAT: An Efficient Privacy-Preserving Statistical Analysis Framework using Homomorphic Encryption
With the widespread adoption of cloud computing, the need for outsourcing statistical analysis to third-party platforms is growing rapidly. However, handling sensitive data such as medical records and financial information in cloud environments raises serious privacy concerns. In this paper, we present PP-STAT, a novel and efficient Homomorphic Encryption (HE)-based framework for privacy-preserving statistical analysis. HE enables computations to be performed directly on encrypted data without …

Judge rejects Meta attempt to overturn Flo privacy verdict https://therecord.media/judge-rejects-meta-attempt-overturn-flo-privacy-lawsuit

Future of Privacy Forum Honors Julie Brill with Career Achievement Award
https://fpf.org/press-releases/future-of-privacy-forum-honors-julie-brill-with-career-achievement-award/
@…

RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detection
Matthias Neuwirth-Trapp, Maarten Bieshaar, Danda Pani Paudel, Luc Van Gool
https://arxiv.org/abs/2508.13878

RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detection
Incremental Learning (IL) trains models sequentially on new data without full retraining, offering privacy, efficiency, and scalability. IL must balance adaptability to new data with retention of old knowledge. However, evaluations often rely on synthetic, simplified benchmarks, obscuring real-world IL performance. To address this, we introduce two Realistic Incremental Object Detection Benchmarks (RICO): Domain RICO (D-RICO) features domain shifts with a fixed class set, and Expanding-Classes …

Trans-XFed: An Explainable Federated Learning for Supply Chain Credit Assessment
Jie Shi, Arno P. J. M. Siebes, Siamak Mehrkanoon
https://arxiv.org/abs/2508.13715 https://

Trans-XFed: An Explainable Federated Learning for Supply Chain Credit Assessment
This paper proposes a Trans-XFed architecture that combines federated learning with explainable AI techniques for supply chain credit assessment. The proposed model aims to address several key challenges, including privacy, information silos, class imbalance, non-identically and independently distributed (Non-IID) data, and model interpretability in supply chain credit assessment. We introduce a performance-based client selection strategy (PBCS) to tackle class imbalance and Non-IID problems. T…

A Case for Urgency


“Gradually, then suddenly.” – Ernest Hemingway

We live in a rapidly developing dictatorship here in the US. We do not know exactly the details on how this will evolve, but we know that surveillance is always core to creating and sustaining a dictatorship. Surveillance provides the dictator with the foundation for suppressing and intimidating any opposition.


Privacy in our communications reduces the effectiveness of surveillance. Not everything we say…

The Promise of Large Language Models in Digital Health: Evidence from Sentiment Analysis in Online Health Communities
Xiancheng Li, Georgios D. Karampatakis, Helen E. Wood, Chris J. Griffiths, Borislava Mihaylova, Neil S. Coulson, Alessio Pasinato, Pietro Panzarasa, Marco Viviani, Anna De Simoni
https://arxiv.org/abs/2508.14032

The Promise of Large Language Models in Digital Health: Evidence from Sentiment Analysis in Online Health Communities
Digital health analytics face critical challenges nowadays. The sophisticated analysis of patient-generated health content, which contains complex emotional and medical contexts, requires scarce domain expertise, while traditional ML approaches are constrained by data shortage and privacy limitations in healthcare settings. Online Health Communities (OHCs) exemplify these challenges with mixed-sentiment posts, clinical terminology, and implicit emotional expressions that demand specialised know…

Roblox partners with Persona to estimate user ages and verify they are 13 , renames Friends to Connections, and says 13 users can message Trusted Connections (Jay Peters/The Verge)
https://www.theverge.com/news/708670/roblox-trusted-connections-age-est…

Roblox will require a facial scan or government ID to have unfiltered chats
Roblox will let people make “Trusted Connections” to chat more freely, but will require that they use a new age estimation tool to verify that they’re over 13.

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
Zhaoyang Chu, Yao Wan, Zhikun Zhang, Di Wang, Zhou Yang, Hongyu Zhang, Pan Zhou, Xuanhua Shi, Hai Jin, David Lo
https://arxiv.org/abs/2509.13755

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit unintended memorization of sensitive training data, enabling verbatim reproduction of confidential information when specifically prompted. To address this issue, several approaches, including training data de-duplication and differential privacy augmentation, have b…

When Secure Aggregation Falls Short: Achieving Long-Term Privacy in Asynchronous Federated Learning for LEO Satellite Networks
Mohamed Elmahallawy, Tie Luo
https://arxiv.org/abs/2508.13425

When Secure Aggregation Falls Short: Achieving Long-Term Privacy in Asynchronous Federated Learning for LEO Satellite Networks
Secure aggregation is a common technique in federated learning (FL) for protecting data privacy from both curious internal entities (clients or server) and external adversaries (eavesdroppers). However, in dynamic and resource-constrained environments such as low Earth orbit (LEO) satellite networks, traditional secure aggregation methods fall short in two aspects: (1) they assume continuous client availability while LEO satellite visibility is intermittent and irregular; (2) they consider priv…

Conflect: Designing Reflective Thinking-Based Contextual Privacy Policy for Mobile Applications
Shuning Zhang, Sixing Tao, Eve He, Yuting Yang, Ying Ma, Ailei Wang, Xin Yi, Hewu Li
https://arxiv.org/abs/2509.12578

Conflect: Designing Reflective Thinking-Based Contextual Privacy Policy for Mobile Applications
Privacy policies are lengthy and complex, leading to user neglect. While contextual privacy policies (CPPs) present information at the point of risk, they may lack engagement and disrupt tasks. We propose Conflect, an interactive CPP for mobile apps, guided by a reflective thinking framework. Through three workshops with experienced designers and researchers, we constructed the design space of reflective thinking-based CPP design, and identified the disconnect between context and action as the …

Meta investors, Zuckerberg settle $8 billion privacy lawsuit tied to Cambridge Analytica scandal https://therecord.media/meta-investors-zuckerberg-settle-privacy-lawsuit

FuboTV agrees to pay $3.4M to settle a 2023 class action lawsuit alleging it violated US and California privacy laws over user data; Fubo denies the claims (Luke Bouma/Cord Cutters News)
https://cordcuttersnews.com/fu…

Fubo May Owe You Money After Agreeing to Pay $3.4 Million to Settle Class Action Lawsuit Over Privacy Violations | Cord Cutters News
FuboTV Inc. and FuboTV Media Inc. have agreed to pay $3.4 million to settle a class action lawsuit alleging the companies violated federal and California privacy laws, including the Video Privacy Protection Act (VPPA), the California Invasion of Privacy Act (CIPA), and California Civil Code § 1799.3. The lawsuit claims Fubo improperly collected, stored, used, […]

Future of Privacy Forum Honors Julie Brill with Lifetime Achievement Award
https://fpf.org/press-releases/future-of-privacy-forum-honors-julie-brill-with-lifetime-achievement-award/
@…

Fight Chat Control – Protect Digital Privacy in the EU: The EU (still) wants to scan your private messages and photos.
The "Chat Control" proposal would mandate scanning of all private digital communications, including encrypted messages and photos. This threatens fundamental privacy rights and digital security for all EU citizens.
🇪🇺 https://

CTFlow: Video-Inspired Latent Flow Matching for 3D CT Synthesis
Jiayi Wang, Hadrien Reynaud, Franciskus Xaverius Erick, Bernhard Kainz
https://arxiv.org/abs/2508.12900 https://

CTFlow: Video-Inspired Latent Flow Matching for 3D CT Synthesis
Generative modelling of entire CT volumes conditioned on clinical reports has the potential to accelerate research through data augmentation, privacy-preserving synthesis and reducing regulator-constraints on patient data while preserving diagnostic signals. With the recent release of CT-RATE, a large-scale collection of 3D CT volumes paired with their respective clinical reports, training large text-conditioned CT volume generation models has become achievable. In this work, we introduce CTFlo…

Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models
Wenxuan Ye, Xueli An, Onur Ayan, Junfan Wang, Xueqiang Yan, Georg Carle
https://arxiv.org/abs/2508.13625

Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models
Large models, renowned for superior performance, outperform smaller ones even without billion-parameter scales. While mobile network servers have ample computational resources to support larger models than client devices, privacy constraints prevent clients from directly sharing their raw data. Federated Learning (FL) enables decentralized clients to collaboratively train a shared model by exchanging model parameters instead of transmitting raw data. Yet, it requires a uniform model architectur…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[8/8]:
- Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation
Feiran Li, Qianqian Xu, Shilong Bao, Boyu Han, Zhiyong Yang, Qingming Huang

Meta shareholders suing Mark Zuckerberg and Meta leaders over Facebook's Cambridge Analytica privacy violations reach a settlement deal, ending an $8B trial (Reuters)
https://www.reuters.com/sustainability/boa…

My Personal Privacy - Your resource for achieving better online privacy
Why privacy:
The right to privacy is a well-established, fundamental human right. It is necessary for a safe and just society. It is especially important in regions where intolerance and discrimination are backed by autocratic regimes. While you may not feel the need for privacy in all of your online activity, you should be able to achieve a high level of privacy when you need it. This website and the document…

A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy
Xiang Li, Yifan Lin, Yuanzhe Zhang
https://arxiv.org/abs/2507.12098

A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy
To mitigate privacy leakage and performance issues in personalized advertising, this paper proposes a framework that integrates federated learning and differential privacy. The system combines distributed feature extraction, dynamic privacy budget allocation, and robust model aggregation to balance model accuracy, communication overhead, and privacy protection. Multi-party secure computing and anomaly detection mechanisms further enhance system resilience against malicious attacks. Experimental…

More than Meets the Eye: Understanding the Effect of Individual Objects on Perceived Visual Privacy
Mete Harun Akcay, Siddharth Prakash Rao, Alexandros Bakas, Buse Gul Atli
https://arxiv.org/abs/2509.13051

More than Meets the Eye: Understanding the Effect of Individual Objects on Perceived Visual Privacy
User-generated content, such as photos, comprises the majority of online media content and drives engagement due to the human ability to process visual information quickly. Consequently, many online platforms are designed for sharing visual content, with billions of photos posted daily. However, photos often reveal more than they intended through visible and contextual cues, leading to privacy risks. Previous studies typically treat privacy as a property of the entire image, overlooking individ…

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
Nobin Sarwar, Shubhashis Roy Dipta
https://arxiv.org/abs/2509.14275 https://

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
Privacy-preserving adaptation of Large Language Models (LLMs) in sensitive domains (e.g., mental health) requires balancing strict confidentiality with model utility and safety. We propose FedMentor, a federated fine-tuning framework that integrates Low-Rank Adaptation (LoRA) and domain-aware Differential Privacy (DP) to meet per-domain privacy budgets while maintaining performance. Each client (domain) applies a custom DP noise scale proportional to its data sensitivity, and the server adaptiv…

New Study Shows Google Tracking Persists Even With Privacy Tools
A new SafetyDetectives study reveals the surprising extent of Google tracking across the web in the US, UK, Switzerland, and Sweden. Discover how Google Analytics, AdSense, and YouTube embeds collect your data, even when using DuckDuckGo.
🕵️ https:…

New Study Shows Google Tracking Persists Even With Privacy Tools
Follow us on Bluesky, Twitter (X), Mastodon and Facebook at @Hackread

A Review of Privacy Metrics for Privacy-Preserving Synthetic Data Generation
Frederik Marinus Trudslev, Matteo Lissandrini, Juan Manuel Rodriguez, Martin B{\o}gsted, Daniele Dell'Aglio
https://arxiv.org/abs/2507.11324

A Review of Privacy Metrics for Privacy-Preserving Synthetic Data Generation
Privacy Preserving Synthetic Data Generation (PP-SDG) has emerged to produce synthetic datasets from personal data while maintaining privacy and utility. Differential privacy (DP) is the property of a PP-SDG mechanism that establishes how protected individuals are when sharing their sensitive data. It is however difficult to interpret the privacy loss ($\varepsilon$) expressed by DP. To make the actual risk associated with the privacy loss more transparent, multiple privacy metrics (PMs) have b…

The “Neural Data” Goldilocks Problem: Defining “Neural Data” in U.S. State Privacy Laws
https://fpf.org/blog/the-neural-data-goldilocks-problem-defining-neural-data-in-u-s-state-privacy-laws/
@…

Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users
Jeffri Murrugarra-LLerena, Haoran Niu, K. Suzanne Barber, Hal Daum\'e III, Yang Trista Cao, Paola Cascante-Bonilla
https://arxiv.org/abs/2508.09245

Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users
As visual assistant systems powered by visual language models (VLMs) become more prevalent, concerns over user privacy have grown, particularly for blind and low vision users who may unknowingly capture personal private information in their images. Existing privacy protection methods rely on coarse-grained segmentation, which uniformly masks entire private objects, often at the cost of usability. In this work, we propose FiGPriv, a fine-grained privacy protection framework that selectively mask…

Federated Multi-Agent Reinforcement Learning for Privacy-Preserving and Energy-Aware Resource Management in 6G Edge Networks
Francisco Javier Esono Nkulu Andong, Qi Min
https://arxiv.org/abs/2509.10163

Federated Multi-Agent Reinforcement Learning for Privacy-Preserving and Energy-Aware Resource Management in 6G Edge Networks
As sixth-generation (6G) networks move toward ultra-dense, intelligent edge environments, efficient resource management under stringent privacy, mobility, and energy constraints becomes critical. This paper introduces a novel Federated Multi-Agent Reinforcement Learning (Fed-MARL) framework that incorporates cross-layer orchestration of both the MAC layer and application layer for energy-efficient, privacy-preserving, and real-time resource management across heterogeneous edge devices. Each age…

GAMA: A General Anonymizing Multi-Agent System for Privacy Preservation Enhanced by Domain Rules and Disproof Method
Hailong Yang, Renhuo Zhao, Guanjin Wang, Zhaohong Deng
https://arxiv.org/abs/2509.10018

GAMA: A General Anonymizing Multi-Agent System for Privacy Preservation Enhanced by Domain Rules and Disproof Method
With the rapid advancement of Large Language Model (LLM), LLM-based agents exhibit exceptional abilities in understanding and generating natural language, facilitating human-like collaboration and information transmission in LLM-based Multi-Agent System (MAS). High-performance LLMs are often hosted on remote servers in public spaces. When tasks involve privacy data, MAS cannot securely utilize these LLMs without implementing privacy-preserving mechanisms. To address this challenge, we propose a…

The trial for an $8B lawsuit by Meta investors against Mark Zuckerberg and other leaders opens over claims tied to the 2018 Cambridge Analytica privacy scandal (Associated Press)
https://apnews.com/article/meta-privacy-cambridge-analyti…

»DuckDuckGo now lets you hide AI-generated images in search results:
Privacy-focused browser DuckDuckGo is rolling out a new setting that lets users filter out AI images in search results. The company says it’s launching the feature in response to feedback from users who said AI images can get in the way of finding what they’re looking for.«
I don't prefer this as my main search engine but if this could not trigger ain anti-AI hype?
🔎

DuckDuckGo now lets you hide AI-generated images in search results | TechCrunch
DuckDuckGo's new search feature comes as the internet is being flooded with AI-generated slop.

DPCheatSheet: Using Worked and Erroneous LLM-usage Examples to Scaffold Differential Privacy Implementation
Shao-Yu Chu, Yuhe Tian, Yu-Xiang Wang, Haojian Jin
https://arxiv.org/abs/2509.12590

DPCheatSheet: Using Worked and Erroneous LLM-usage Examples to Scaffold Differential Privacy Implementation
This paper explores how programmers without specialized expertise in differential privacy (DP) (i.e., novices) can leverage LLMs to implement DP programs with minimal training. We first conducted a need-finding study with 6 novices and 3 experts to understand how they utilize LLMs in DP implementation. While DP experts can implement correct DP analyses through a few prompts, novices struggle to articulate their requirements in prompts and lack the skills to verify the correctness of the generat…

FuSeFL: Fully Secure and Scalable Cross-Silo Federated Learning
Sahar Ghoflsaz Ghinani, Elaheh Sadredini
https://arxiv.org/abs/2507.13591 https://

FuSeFL: Fully Secure and Scalable Cross-Silo Federated Learning
Federated Learning (FL) enables collaborative model training without centralizing client data, making it attractive for privacy-sensitive domains. While existing approaches employ cryptographic techniques such as homomorphic encryption, differential privacy, or secure multiparty computation to mitigate inference attacks-including model inversion, membership inference, and gradient leakage-they often suffer from high computational, communication, or memory overheads. Moreover, many methods overl…

RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation System
Abdolazim Rezaei, Mehdi Sookhak, Mahboobeh Haghparast
https://arxiv.org/abs/2508.09186 ht…

RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation System
The proliferation of AI-powered cameras in Intelligent Transportation Systems (ITS) creates a severe conflict between the need for rich visual data and the fundamental right to privacy. Existing privacy-preserving mechanisms, such as blurring or encryption, are often insufficient, creating an undesirable trade-off where either privacy is compromised against advanced reconstruction attacks or data utility is critically degraded. To resolve this impasse, we propose RL-MoE, a novel framework that …

iTrace: Click-Based Gaze Visualization on the Apple Vision Pro
Esra Mehmedova, Santiago Berrezueta-Guzman, Stefan Wagner
https://arxiv.org/abs/2508.12268 https://

iTrace: Click-Based Gaze Visualization on the Apple Vision Pro
The Apple Vision Pro is equipped with accurate eye-tracking capabilities, yet the privacy restrictions on the device prevent direct access to continuous user gaze data. This study introduces iTrace, a novel application that overcomes these limitations through click-based gaze extraction techniques, including manual methods like a pinch gesture, and automatic approaches utilizing dwell control or a gaming controller. We developed a system with a client-server architecture that captures the gaze …

Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods
Jaeung Lee, Suhyeon Yu, Yurim Jang, Simon S. Woo, Jaemin Jo
https://arxiv.org/abs/2508.12730

Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods
Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer influences the model's behavior, fulfilling "right to be forgotten" obligations under data privacy laws. Yet, we observe that researchers in this rapidly emerging field face challenges in analyzing and understanding the behavior of different MU methods, especially in terms of three fundamental principles in MU: accuracy, efficiency, and privacy. Consequently, they often rely on ag…

Immersive Invaders: Privacy Threats from Deceptive Design in Virtual Reality Games and Applications
Hilda Hadan, Michaela Valiquette, Lennart E. Nacke, Leah Zhang-Kennedy
https://arxiv.org/abs/2509.09916

Immersive Invaders: Privacy Threats from Deceptive Design in Virtual Reality Games and Applications
Virtual Reality (VR) technologies offer immersive experiences but collect substantial user data. While deceptive design is well-studied in 2D platforms, little is known about its manifestation in VR environments and its impact on user privacy. This research investigates deceptive designs in privacy communication and interaction mechanisms of 12 top-rated VR games and applications through autoethnographic evaluation of the applications and thematic analysis of privacy policies. We found that whi…

KV-Auditor: Auditing Local Differential Privacy for Correlated Key-Value Estimation
Jingnan Xu, Leixia Wang, Xiaofeng Meng
https://arxiv.org/abs/2508.11495 https://

KV-Auditor: Auditing Local Differential Privacy for Correlated Key-Value Estimation
To protect privacy for data-collection-based services, local differential privacy (LDP) is widely adopted due to its rigorous theoretical bound on privacy loss. However, mistakes in complex theoretical analysis or subtle implementation errors may undermine its practical guarantee. To address this, auditing is crucial to confirm that LDP protocols truly protect user data. However, existing auditing methods, though, mainly target machine learning and federated learning tasks based on centralized …

Practitioners' Perspectives on a Differential Privacy Deployment Registry
Priyanka Nanayakkara, Elena Ghazi, Salil Vadhan
https://arxiv.org/abs/2509.13509 https://

Practitioners' Perspectives on a Differential Privacy Deployment Registry
Differential privacy (DP) -- a principled approach to producing statistical data products with strong, mathematically provable privacy guarantees for the individuals in the underlying dataset -- has seen substantial adoption in practice over the past decade. Applying DP requires making several implementation decisions, each with significant impacts on data privacy and/or utility. Hence, to promote shared learning and accountability around DP deployments, Dwork, Kohli, and Mulligan (2019) propos…

Using Real Names of Disabled Participant-Contributors to Practice Citational Justice in Accessibility
Jonathan Zong
https://arxiv.org/abs/2508.14257 https://

Using Real Names of Disabled Participant-Contributors to Practice Citational Justice in Accessibility
In accessibility research involving human subjects, researchers conventionally anonymize their research participants to protect privacy. However, a lack of intentionality about who to publicly acknowledge for intellectual contributions to research can lead to the erasure of disabled individuals' work and knowledge. In this paper, I propose identifying disabled research participants by name (with consent) as a practice of citational justice. I share observations from examples of this practice in…

Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Response
Ozer Ozturk, Busra Buyuktanir, Gozde Karatas Baydogmus, Kazim Yildiz
https://arxiv.org/abs/2509.13987

Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Response
Machine learning models used for distributed architectures consisting of servers and clients require large amounts of data to achieve high accuracy. Data obtained from clients are collected on a central server for model training. However, storing data on a central server raises concerns about security and privacy. To address this issue, a federated learning architecture has been proposed. In federated learning, each client trains a local model using its own data. The trained models are periodic…

Secure, Scalable and Privacy Aware Data Strategy in Cloud
Vijay Kumar Butte, Sujata Butte
https://arxiv.org/abs/2509.13627 https://arxiv.org/pdf/2509.13627…

Secure, Scalable and Privacy Aware Data Strategy in Cloud
The enterprises today are faced with the tough challenge of processing, storing large amounts of data in a secure, scalable manner and enabling decision makers to make quick, informed data driven decisions. This paper addresses this challenge and develops an effective enterprise data strategy in the cloud. Various components of an effective data strategy are discussed and architectures addressing security, scalability and privacy aspects are provided.

Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption
Nges Brian Njungle, Michel A. Kinsy
https://arxiv.org/abs/2508.11575

Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption
The growing adoption of machine learning in sensitive areas such as healthcare and defense introduces significant privacy and security challenges. These domains demand robust data protection, as models depend on large volumes of sensitive information for both training and inference. Fully Homomorphic Encryption (FHE) presents a compelling solution by enabling computations directly on encrypted data, maintaining confidentiality across the entire machine learning workflow. However, FHE inherently…

Piquant$\varepsilon$: Private Quantile Estimation in the Two-Server Model
Hannah Keller, Jacob Imola, Fabrizio Boninsegna, Rasmus Pagh, Amrita Roy Chowdhury
https://arxiv.org/abs/2509.14035

Piquant$\varepsilon$: Private Quantile Estimation in the Two-Server Model
Quantiles are key in distributed analytics, but computing them over sensitive data risks privacy. Local differential privacy (LDP) offers strong protection but lower accuracy than central DP, which assumes a trusted aggregator. Secure multi-party computation (MPC) can bridge this gap, but generic MPC solutions face scalability challenges due to large domains, complex secure operations, and multi-round interactions. We present Piquant$\varepsilon$, a system for privacy-preserving estimation of…

Unveiling Usability Challenges in Web Privacy Controls
Rahat Masood, Sunday Oyinlola Ogundoyin, Muhammad Ikram, Alex Ye
https://arxiv.org/abs/2507.11908 ht…

Unveiling Usability Challenges in Web Privacy Controls
With the increasing concerns around privacy and the enforcement of data privacy laws, many websites now provide users with privacy controls. However, locating these controls can be challenging, as they are frequently hidden within multiple settings and layers. Moreover, the lack of standardization means these controls can vary widely across services. The technical or confusing terminology used to describe these controls further complicates users' ability to understand and use them effectively. …

Efficient Byzantine-Robust Privacy-Preserving Federated Learning via Dimension Compression
Xian Qin, Xue Yang, Xiaohu Tang
https://arxiv.org/abs/2509.11870 https://

Efficient Byzantine-Robust Privacy-Preserving Federated Learning via Dimension Compression
Federated Learning (FL) allows collaborative model training across distributed clients without sharing raw data, thus preserving privacy. However, the system remains vulnerable to privacy leakage from gradient updates and Byzantine attacks from malicious clients. Existing solutions face a critical trade-off among privacy preservation, Byzantine robustness, and computational efficiency. We propose a novel scheme that effectively balances these competing objectives by integrating homomorphic encr…

EByFTVeS: Efficient Byzantine Fault Tolerant-based Verifiable Secret-sharing in Distributed Privacy-preserving Machine Learning
Zhen Li, Zijian Zhang, Wenjin Yang, Pengbo Wang, Zhaoqi Wang, Meng Li, Yan Wu, Xuyang Liu, Jing Sun, Liehuang Zhu
https://arxiv.org/abs/2509.12899

EByFTVeS: Efficient Byzantine Fault Tolerant-based Verifiable Secret-sharing in Distributed Privacy-preserving Machine Learning
Verifiable Secret Sharing (VSS) has been widespread in Distributed Privacy-preserving Machine Learning (DPML), because invalid shares from malicious dealers or participants can be recognized by verifying the commitment of the received shares for honest participants. However, the consistency and the computation and communitation burden of the VSS-based DPML schemes are still two serious challenges. Although Byzantine Fault Tolerance (BFT) system has been brought to guarantee the consistency and …

Make Identity Unextractable yet Perceptible: Synthesis-Based Privacy Protection for Subject Faces in Photos
Tao Wang, Yushu Zhang, Xiangli Xiao, Kun Xu, Lin Yuan, Wenying Wen, Yuming Fang
https://arxiv.org/abs/2509.11249

Make Identity Unextractable yet Perceptible: Synthesis-Based Privacy Protection for Subject Faces in Photos
Deep learning-based face recognition (FR) technology exacerbates privacy concerns in photo sharing. In response, the research community developed a suite of anti-FR methods to block identity extraction by unauthorized FR systems. Benefiting from quasi-imperceptible alteration, perturbation-based methods are well-suited for privacy protection of subject faces in photos, as they allow familiar persons to recognize subjects via naked eyes. However, we reveal that perturbation-based methods provide…

Silentflow: Leveraging Trusted Execution for Resource-Limited MPC via Hardware-Algorithm Co-design
Zhuoran Li, Hanieh Totonchi Asl, Ebrahim Nouri, Yifei Cai, Danella Zhao
https://arxiv.org/abs/2508.13357

Silentflow: Leveraging Trusted Execution for Resource-Limited MPC via Hardware-Algorithm Co-design
Secure Multi-Party Computation (MPC) offers a practical foundation for privacy-preserving machine learning at the edge, with MPC commonly employed to support nonlinear operations. These MPC protocols fundamentally rely on Oblivious Transfer (OT), particularly Correlated OT (COT), to generate correlated randomness essential for secure computation. Although COT generation is efficient in conventional two-party settings with resource-rich participants, it becomes a critical bottleneck in real-worl…

Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes
Zilong Lin, Zichuan Li, Xiaojing Liao, XiaoFeng Wang
https://arxiv.org/abs/2508.12622

Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes
The advancement of AI technologies, particularly Large Language Models (LLMs), has transformed computing while introducing new security and privacy risks. Prior research shows that cybercriminals are increasingly leveraging uncensored LLMs (ULLMs) as backends for malicious services. Understanding these ULLMs has been hindered by the challenge of identifying them among the vast number of open-source LLMs hosted on platforms like Hugging Face. In this paper, we present the first systematic study …

ToxiEval-ZKP: A Structure-Private Verification Framework for Molecular Toxicity Repair Tasks
Fei Lin, Tengchao Zhang, Ziyang Gong, Fei-Yue Wang
https://arxiv.org/abs/2508.12035 …

ToxiEval-ZKP: A Structure-Private Verification Framework for Molecular Toxicity Repair Tasks
In recent years, generative artificial intelligence (GenAI) has demonstrated remarkable capabilities in high-stakes domains such as molecular science. However, challenges related to the verifiability and structural privacy of its outputs remain largely unresolved. This paper focuses on the task of molecular toxicity repair. It proposes a structure-private verification framework - ToxiEval-ZKP - which, for the first time, introduces zero-knowledge proof (ZKP) mechanisms into the evaluation proce…

CryptPEFT: Efficient and Private Neural Network Inference via Parameter-Efficient Fine-Tuning
Saisai Xia, Wenhao Wang, Zihao Wang, Yuhui Zhang, Yier Jin, Dan Meng, Rui Hou
https://arxiv.org/abs/2508.12264

CryptPEFT: Efficient and Private Neural Network Inference via Parameter-Efficient Fine-Tuning
Publicly available large pretrained models (i.e., backbones) and lightweight adapters for parameter-efficient fine-tuning (PEFT) have become standard components in modern machine learning pipelines. However, preserving the privacy of both user inputs and fine-tuned adapters -- often trained on sensitive data -- during inference remains a significant challenge. Applying cryptographic techniques, such as multi-party computation (MPC), to PEFT settings still incurs substantial encrypted computatio…

Threats and Security Strategies for IoMT Infusion Pumps
Ramazan Yener, Muhammad Hassan, Masooda Bashir
https://arxiv.org/abs/2509.14604 https://arxiv.org/p…

Threats and Security Strategies for IoMT Infusion Pumps
The integration of the Internet of Medical Things (IoMT) into healthcare systems has transformed patient care by enabling real-time monitoring, enhanced diagnostics, and enhanced operational efficiency. However, this increased connectivity has also expanded the attack surface for cybercriminals, raising significant cybersecurity and privacy concerns. This study focuses on the cybersecurity vulnerabilities of IoMT infusion pumps, which are critical devices in modern healthcare. Through a targete…

Security Analysis of Web Applications Based on Gruyere
Yonghao Ni, Zhongwen Li, Xiaoqi Li
https://arxiv.org/abs/2509.14706 https://arxiv.org/pdf/2509.14706…

Security Analysis of Web Applications Based on Gruyere
With the rapid development of Internet technologies, web systems have become essential infrastructures for modern information exchange and business operations. However, alongside their expansion, numerous security vulnerabilities have emerged, making web security a critical research focus within the broader field of cybersecurity. These issues are closely related to data protection, privacy preservation, and business continuity, and systematic research on web security is crucial for mitigating …

Searching for Privacy Risks in LLM Agents via Simulation
Yanzhe Zhang, Diyi Yang
https://arxiv.org/abs/2508.10880 https://arxiv.org/pdf/2508.10880

Searching for Privacy Risks in LLM Agents via Simulation
The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. These dynamic dialogues enable adaptive attack strategies that can cause severe privacy violations, yet their evolving nature makes it difficult to anticipate and discover sophisticated vulnerabilities manually. To tackle this problem, we present a search-based framework that alternates betwee…