Tootfinder

FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
Nicol\`o Romandini, Cristian Borcea, Rebecca Montanari, Luca Foschini
https://arxiv.org/abs/2508.13853

FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
Federated Learning (FL) can be vulnerable to attacks, such as model poisoning, where adversaries send malicious local weights to compromise the global model. Federated Unlearning (FU) is emerging as a solution to address such vulnerabilities by selectively removing the influence of detected malicious contributors on the global model without complete retraining. However, unlike typical FU scenarios where clients are trusted and cooperative, applying FU with malicious and possibly colluding clien…

PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning
Xiangman Li, Xiaodong Wu, Jianbing Ni, Mohamed Mahmoud, Maazen Alsabaan
https://arxiv.org/abs/2506.15112

PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning
Decentralized learning is vulnerable to poison attacks, where malicious clients manipulate local updates to degrade global model performance. Existing defenses mainly detect and filter malicious models, aiming to prevent a limited number of attackers from corrupting the global model. However, restoring an already compromised global model remains a challenge. A direct approach is to remove malicious clients and retrain the model using only the benign clients. Yet, retraining is time-consuming, c…

packet_delays: Internet packet delays (2002)
A network representing the difference in delay observed by packet probes sent from a computer at Rice University to similar machines at different universities, in c.2002. The edge weight denotes the difference in delay of the packet in milliseconds.
This network has 10 nodes and 9567 edges.
Tags: Technological, Communication, Weighted

Mollissez pas, je compte bien faire une capture d'écran au passage du million. #DuplombDansLAile

“Specifically, InfoFlood: (1) uses linguistic transformations to rephrase malicious queries, (2) identifies the root cause of failure when an attempt is unsuccessful, and (3) refines the prompt’s linguistic structure to address the failure while preserving its malicious intent.”
#LLM #AI

Sub-Millisecond Event-Based Eye Tracking on a Resource-Constrained Microcontroller
Marco Giordano, Pietro Bonazzi, Luca Benini, Michele Magno
https://arxiv.org/abs/2508.13244 ht…

Sub-Millisecond Event-Based Eye Tracking on a Resource-Constrained Microcontroller
This paper presents a novel event-based eye-tracking system deployed on a resource-constrained microcontroller, addressing the challenges of real-time, low-latency, and low-power performance in embedded systems. The system leverages a Dynamic Vision Sensor (DVS), specifically the DVXplorer Micro, with an average temporal resolution of 200 μs, to capture rapid eye movements with extremely low latency. The system is implemented on a novel low-power and high-performance microcontroller from STMic…

This story is cute: A malicious "Solidity" (that's the smart contract language Ethereum and other blockchains use) extension for Cursor, the Vibe-Coding Editor included code that steals your tokens/coins.
I find it funny for two reasons:
- Blockchainers love talking about how you need to verify things you interact with but someone wasn't checking if they have the right extension
- Programming smart contracts is hard because it's a massively hostile envir…

Code highlighting with Cursor AI for $500,000
Kaspersky GReAT experts uncover malicious extensions for Cursor AI that download the Quasar backdoor and a crypto stealer.

i was put in charge of three grandchildren for a few hours yesterday so we headed straight to ben & jerry's to split a milkshake, then explored the state theater (and even sneaked into a movie but later got thrown out for horsing around on the escalator), then i gave a nickel tour of angell/mason/haven halls, then they chased squirrels on the diag which took longer than you might think, then we looked in all the windows in nickels arcade. it all went slowly and well.

Beneath the Mask: Can Contribution Data Unveil Malicious Personas in Open-Source Projects?
Ruby Nealon
https://arxiv.org/abs/2508.13453 https://arxiv.org/p…

Beneath the Mask: Can Contribution Data Unveil Malicious Personas in Open-Source Projects?
In February 2024, after building trust over two years with project maintainers by making a significant volume of legitimate contributions, GitHub user "JiaT75" self-merged a version of the XZ Utils project containing a highly sophisticated, well-disguised backdoor targeting sshd processes running on systems with the backdoored package installed. A month later, this package began to be distributed with popular Linux distributions until a Microsoft employee discovered the backdoor while investiga…

Privacy-Preserving Federated Learning against Malicious Clients Based on Verifiable Functional Encryption
Nina Cai, Jinguang Han
https://arxiv.org/abs/2506.12846

Privacy-Preserving Federated Learning against Malicious Clients Based on Verifiable Functional Encryption
Federated learning is a promising distributed learning paradigm that enables collaborative model training without exposing local client data, thereby protect data privacy. However, it also brings new threats and challenges. The advancement of model inversion attacks has rendered the plaintext transmission of local models insecure, while the distributed nature of federated learning makes it particularly vulnerable to attacks raised by malicious clients. To protect data privacy and prevent malici…