Tootfinder

Toby Walsh on AI's vs intellectual property - #UNSW
https://www.youtube.com/watch?v=Puo6CmF5V58

EditMF: Drawing an Invisible Fingerprint for Your Large Language Models
Jiaxuan Wu, Yinghan Zhou, Wanli Peng, Yiming Xue, Juan Wen, Ping Zhong
https://arxiv.org/abs/2508.08836 h…

EditMF: Drawing an Invisible Fingerprint for Your Large Language Models
Training large language models (LLMs) is resource-intensive and expensive, making protecting intellectual property (IP) for LLMs crucial. Recently, embedding fingerprints into LLMs has emerged as a prevalent method for establishing model ownership. However, existing back-door-based methods suffer from limited stealth and efficiency. To simultaneously address these issues, we propose EditMF, a training-free fingerprinting paradigm that achieves highly imperceptible fingerprint embedding with min…

Dark prediction:
- Intellectual Property Class Action against AI companies gains traction
- AI companies use this as a plausible excuse to bail on AGI tech (that doesn’t exist)
- We see a pop like we saw “shipping heavy items by mail isn’t sustainable?!” pop in 2001
- AI companies fail, overwhelmingly, blaming only the IP Class Action
- The Money switches to a new/old grift; maybe back to crypto… lots of GPUs available
- In 5 years, everyone forgets and we have…

Matrix-Driven Instant Review: Confident Detection and Reconstruction of LLM Plagiarism on PC
Ruichong Zhang
https://arxiv.org/abs/2508.06309 https://arxiv.…

Matrix-Driven Instant Review: Confident Detection and Reconstruction of LLM Plagiarism on PC
In recent years, concerns about intellectual property (IP) in large language models (LLMs) have grown significantly. Plagiarizing other LLMs (through direct weight copying, upcycling, pruning, or continual pretraining) and claiming authorship without properly attributing to the original license, is a serious misconduct that can lead to significant financial and reputational harm to the original developers. However, existing methods for detecting LLM plagiarism fall short in key areas. They fail…

Real-world Music Plagiarism Detection With Music Segment Transcription System
Seonghyeon Go
https://arxiv.org/abs/2509.08282 https://arxiv.org/pdf/2509.082…

Real-world Music Plagiarism Detection With Music Segment Transcription System
As a result of continuous advances in Music Information Retrieval (MIR) technology, generating and distributing music has become more diverse and accessible. In this context, interest in music intellectual property protection is increasing to safeguard individual music copyrights. In this work, we propose a system for detecting music plagiarism by combining various MIR technologies. We developed a music segment transcription system that extracts musically meaningful segments from audio recordin…

Designing with Deception: ML- and Covert Gate-Enhanced Camouflaging to Thwart IC Reverse Engineering
Junling Fan, David Koblah, Domenic Forte
https://arxiv.org/abs/2508.08462 ht…

Designing with Deception: ML- and Covert Gate-Enhanced Camouflaging to Thwart IC Reverse Engineering
Integrated circuits (ICs) are essential to modern electronic systems, yet they face significant risks from physical reverse engineering (RE) attacks that compromise intellectual property (IP) and overall system security. While IC camouflage techniques have emerged to mitigate these risks, existing approaches largely focus on localized gate modifications, neglecting comprehensive deception strategies. To address this gap, we present a machine learning (ML)-driven methodology that integrates cryp…

A look at the impact of AI voice cloning on India's dubbing and voiceover sector, as artists demand consent, credit, and fair pay amid a lack of laws for AI use (Zico Ghosh/The Hollywood Reporter)
https://www.hollywoodreporter.com/movies/m

AI Is Replacing Voice Artists in India — and There Are No Local Laws to Stop It
As AI voice cloning in films becomes a reality, India’s dubbing artists are demanding consent, credit and fair pay: "You must understand that your voice is your intellectual property."

Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models
Shiqian Zhao, Chong Wang, Yiming Li, Yihao Huang, Wenjie Qu, Siew-Kei Lam, Yi Xie, Kangjie Chen, Jie Zhang, Tianwei Zhang
https://arxiv.org/abs/2508.06837

Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models
Text-to-Image (T2I) models, represented by DALL$\cdot$E and Midjourney, have gained huge popularity for creating realistic images. The quality of these images relies on the carefully engineered prompts, which have become valuable intellectual property. While skilled prompters showcase their AI-generated art on markets to attract buyers, this business incidentally exposes them to \textit{prompt stealing attacks}. Existing state-of-the-art attack techniques reconstruct the prompts from a fixed se…

A look at the impact of AI voice cloning on India's dubbing and voiceover sector, as artists demand consent, credit, and fair pay amid a lack of laws for AI use (Zico Ghosh/The Hollywood Reporter)
https://www.hollywoodreporter.com/movies/m

AI Is Replacing Voice Artists in India — and There Are No Local Laws to Stop It
As AI voice cloning in films becomes a reality, India’s dubbing artists are demanding consent, credit and fair pay: "You must understand that your voice is your intellectual property."

KLIPA: A Knowledge Graph and LLM-Driven QA Framework for IP Analysis
Guanzhi Deng, Yi Xie, Yu-Keung Ng, Mingyang Liu, Peijun Zheng, Jie Liu, Dapeng Wu, Yinqiao Li, Linqi Song
https://arxiv.org/abs/2509.07860

KLIPA: A Knowledge Graph and LLM-Driven QA Framework for IP Analysis
Effectively managing intellectual property is a significant challenge. Traditional methods for patent analysis depend on labor-intensive manual searches and rigid keyword matching. These approaches are often inefficient and struggle to reveal the complex relationships hidden within large patent datasets, hindering strategic decision-making. To overcome these limitations, we introduce KLIPA, a novel framework that leverages a knowledge graph and a large language model (LLM) to significantly adva…

Intellectual Property Rights and Entrepreneurship in the NFT Ecosystem: Legal Frameworks, Business Models, and Innovation Opportunities
Pranav Darshan, Rohan J S, Raghuveer Rajesh, Ruchitha M, Sanika Kamath, Manas M N
https://arxiv.org/abs/2507.00172

Intellectual Property Rights and Entrepreneurship in the NFT Ecosystem: Legal Frameworks, Business Models, and Innovation Opportunities
Non Fungible Tokens have changed digital ownership and how creators earn money. Between 2021 and 2024, the market value exceeded 40 billion. However, the fast growth of the NFT ecosystem has revealed serious issues in managing intellectual property rights. There is a lot of confusion about the difference between owning an NFT and owning the copyright for the underlying content. This research looks at the gap between traditional copyright laws and blockchain-based transactions. We use a mixed me…

Feds seek to claim $5 million in bitcoin taken in SIM swaps https://therecord.media/us-seeks-5-million-bitcoin-taken-in-sim-swaps

Principle-Guided Verilog Optimization: IP-Safe Knowledge Transfer via Local-Cloud Collaboration
Jing Wang, Zheng Li, Lei Li, Fan He, Liyu Lin, Yao Lai, Yan Li, Xiaoyang Zeng, Yufeng Guo
https://arxiv.org/abs/2508.05675

Principle-Guided Verilog Optimization: IP-Safe Knowledge Transfer via Local-Cloud Collaboration
Recent years have witnessed growing interest in adopting large language models (LLMs) for Register Transfer Level (RTL) code optimization. While powerful cloud-based LLMs offer superior optimization capabilities, they pose unacceptable intellectual property (IP) leakage risks when processing proprietary hardware designs. In this paper, we propose a new scenario where Verilog code must be optimized for specific attributes without leaking sensitive IP information. We introduce the first IP-preser…

Went to Threads to check if we're there yet with the federation of the eurotrash portion of the userbase. Found Zuck's currently busy no-commenting to a bunch of angry writers whose books he used to train his AI.

International Trade and Intellectual Property
Gaetan de Rassenfosse
https://arxiv.org/abs/2506.18929 https://arxiv.org/pdf/2506.18929…

International Trade and Intellectual Property
Intellectual property (IP) rules have the potential to shape cross-border trade far more than their legalistic origins might suggest. Drawing on three decades of evidence, this review shows that stronger IP rights simultaneously create market-power forces that raise prices and market-expansion forces that broaden demand, while dynamic incentives spur quality upgrading and new export varieties. Micro-data and quasi-natural experiments after TRIPS reveal that IP most often boosts trade along the …

Agency, Affordances, and Enculturation of Augmentation Technologies
Ann Hill Duin, Isabel Pedersen
https://arxiv.org/abs/2508.04725 https://arxiv.org/pdf/2…

Agency, Affordances, and Enculturation of Augmentation Technologies
Augmentation technologies are undergoing a process of enculturation due to many factors, one being the rise of artificial intelligence (AI), or what the World Intellectual Property Organization (WIPO) terms the AI wave or AI boom. Chapter 3 focuses critical attention on the hyped assumption that sophisticated, emergent, and embodied augmentation technologies will improve lives, literacy, cultures, arts, economies, and social contexts. The chapter begins by discussing the problem of ambiguity wi…

Patents as Knowledge Artifacts: An Information Science Perspective on Global Innovation
M. S. Rajeevan, B. Mini Devi
https://arxiv.org/abs/2508.00871 https://

Patents as Knowledge Artifacts: An Information Science Perspective on Global Innovation
In an age of fast-paced technological change, patents have evolved into not only legal mechanisms of intellectual property, but also structured storage containers of knowledge full of metadata, categories, and formal innovation. This chapter proposes to reframe patents in the context of information science, by focusing on patents as knowledge artifacts, and by seeing patents as fundamentally tied to the global movement of scientific and technological knowledge. With a focus on three areas, the …

The NFL strikes a licensing deal with Front Office Sports, the first time the NFL has partnered with a sports business-focused news outlet to share content (Sara Fischer/Axios)
https://www.axios.com/2025/09/02/nfl-front-office-sports-content-deal

Exclusive: NFL strikes content deal with Front Office Sports
The yearlong deal will give FOS access to NFL intellectual property.

Staining and locking computer vision models without retraining
Oliver J. Sutton, Qinghua Zhou, George Leete, Alexander N. Gorban, Ivan Y. Tyukin
https://arxiv.org/abs/2507.22000

Staining and locking computer vision models without retraining
We introduce new methods of staining and locking computer vision models, to protect their owners' intellectual property. Staining, also known as watermarking, embeds secret behaviour into a model which can later be used to identify it, while locking aims to make a model unusable unless a secret trigger is inserted into input images. Unlike existing methods, our algorithms can be used to stain and lock pre-trained models without requiring fine-tuning or retraining, and come with provable, comput…

Dont use We Transfer

Now, even if you do want next token prediction:
Was it really worth the billions of dollars, the pollution, the pure disdain for the intellectual property of authors, to get here?
*I* don't think so. Predicting text is cute, it's fun, it's a party trick I would value at ~$100. I wouldn't make it my fucking life's work, but I guess we all have different value frameworks.

Never Trust the Manufacturer, Never Trust the Client: A Novel Method for Streaming STL Files for Secure Additive
Seyed Ali Ghazi Asgar, Narasimha Reddy, Satish T. S. Bukkapatnam
https://arxiv.org/abs/2507.06421

Never Trust the Manufacturer, Never Trust the Client: A Novel Method for Streaming STL Files for Secure Additive
While additive manufacturing has opened interesting avenues to reimagine manufacturing as a service (MaaS) platform, transmission of design files from client to manufacturer over networks opens up many cybersecurity challenges. Securing client's intellectual property (IP) especially from cyber-attacks emerges as a major challenge. Earlier works introduced streaming, instead of sharing process plan (G-code) files, as a possible solution. However, executing client's G-codes on manufacturer's mach…

Stylometry recognizes human and LLM-generated texts in short samples
Karol Przystalski, Jan K. Argasi\'nski, Iwona Grabska-Gradzi\'nska, Jeremi K. Ochab
https://arxiv.org/abs/2507.00838

Stylometry recognizes human and LLM-generated texts in short samples
The paper explores stylometry as a method to distinguish between texts created by Large Language Models (LLMs) and humans, addressing issues of model attribution, intellectual property, and ethical AI use. Stylometry has been used extensively to characterise the style and attribute authorship of texts. By applying it to LLM-generated texts, we identify their emergent writing patterns. The paper involves creating a benchmark dataset based on Wikipedia, with (a) human-written term summaries, (b) …

Have you read the new Wetransfer's terms of service?
"In order to allow us to operate, provide you with, and improve the Service and our technologies, we must obtain from you certain rights related to Content that is covered by intellectual property rights. You hereby grant us royalty a-free license to use your Content for the purposes of operating, developing, and improving the Service, all in accordance with our Privacy & Cookie Policy. (...) You hereby grant other users…

Investigating Training Data Detection in AI Coders
Tianlin Li, Yunxiang Wei, Zhiming Li, Aishan Liu, Qing Guo, Xianglong Liu, Dongning Sun, Yang Liu
https://arxiv.org/abs/2507.17389

Investigating Training Data Detection in AI Coders
Recent advances in code large language models (CodeLLMs) have made them indispensable tools in modern software engineering. However, these models occasionally produce outputs that contain proprietary or sensitive code snippets, raising concerns about potential non-compliant use of training data, and posing risks to privacy and intellectual property. To ensure responsible and compliant deployment of CodeLLMs, training data detection (TDD) has become a critical task. While recent TDD methods have…

Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses
Lincan Li, Bolin Shen, Chenxi Zhao, Yuxiang Sun, Kaixiang Zhao, Shirui Pan, Yushun Dong
https://arxiv.org/abs/2508.19641

Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses
Graph-structured data, which captures non-Euclidean relationships and interactions between entities, is growing in scale and complexity. As a result, training state-of-the-art graph machine learning (GML) models have become increasingly resource-intensive, turning these models and data into invaluable Intellectual Property (IP). To address the resource-intensive nature of model training, graph-based Machine-Learning-as-a-Service (GMLaaS) has emerged as an efficient solution by leveraging third-…

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!
Do-hyeon Yoon, Minsoo Chun, Thomas Allen, Hans M\"uller, Min Wang, Rajesh Sharma
https://arxiv.org/abs/2507.03014

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!
Large language models (LLMs) face significant copyright and intellectual property challenges as the cost of training increases and model reuse becomes prevalent. While watermarking techniques have been proposed to protect model ownership, they may not be robust to continue training and development, posing serious threats to model attribution and copyright protection. This work introduces a simple yet effective approach for robust LLM fingerprinting based on intrinsic model characteristics. We d…

Distilled Large Language Model in Confidential Computing Environment for System-on-Chip Design
Dong Ben, Hui Feng, Qian Wang
https://arxiv.org/abs/2507.16226

Distilled Large Language Model in Confidential Computing Environment for System-on-Chip Design
Large Language Models (LLMs) are increasingly used in circuit design tasks and have typically undergone multiple rounds of training. Both the trained models and their associated training data are considered confidential intellectual property (IP) and must be protected from exposure. Confidential Computing offers a promising solution to protect data and models through Trusted Execution Environments (TEEs). However, existing TEE implementations are not designed to support the resource-intensive n…

VLA-Mark: A cross modal watermark for large vision-language alignment model
Shuliang Liu, Qi Zheng, Jesse Jiaxi Xu, Yibo Yan, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, Xuming Hu
https://arxiv.org/abs/2507.14067

VLA-Mark: A cross modal watermark for large vision-language alignment model
Vision-language models demand watermarking solutions that protect intellectual property without compromising multimodal coherence. Existing text watermarking methods disrupt visual-textual alignment through biased token selection and static strategies, leaving semantic-critical concepts vulnerable. We propose VLA-Mark, a vision-aligned framework that embeds detectable watermarks while preserving semantic fidelity through cross-modal coordination. Our approach integrates multiscale visual-textua…

Watermarking Large Language Model-based Time Series Forecasting
Wei Yuan, Chaoqun Yang, Yu Xing, Tong Chen, Nguyen Quoc Viet Hung, Hongzhi Yin
https://arxiv.org/abs/2507.20762 h…

Watermarking Large Language Model-based Time Series Forecasting
Large Language Model-based Time Series Forecasting (LLMTS) has shown remarkable promise in handling complex and diverse temporal data, representing a significant step toward foundation models for time series analysis. However, this emerging paradigm introduces two critical challenges. First, the substantial commercial potential and resource-intensive development raise urgent concerns about intellectual property (IP) protection. Second, their powerful time series forecasting capabilities may be …

Securing Transformer-based AI Execution via Unified TEE and Crypto-protected Accelerators
Jiaqi Xue, Yifei Zhao, Mengxin Zheng, Xun Chen, Fan Yao, Yan Solihin, Qian Lou
https://arxiv.org/abs/2507.03278

Securing Transformer-based AI Execution via Unified TEE and Crypto-protected Accelerators
Recent advances in Transformer models, e.g., large language models (LLMs), have brought tremendous breakthroughs in various artificial intelligence (AI) tasks, leading to their wide applications in many security-critical domains. Due to their unprecedented scale and prohibitively high development cost, these models have become highly valuable intellectual property for AI stakeholders and are increasingly deployed via machine learning as a service (MLaaS). However, MLaaS often runs on untrusted …

An automatic patent literature retrieval system based on LLM-RAG
Yao Ding, Yuqing Wu, Ziyang Ding
https://arxiv.org/abs/2508.14064 https://arxiv.org/pdf/25…

An automatic patent literature retrieval system based on LLM-RAG
With the acceleration of technological innovation efficient retrieval and classification of patent literature have become essential for intellectual property management and enterprise RD Traditional keyword and rulebased retrieval methods often fail to address complex query intents or capture semantic associations across technical domains resulting in incomplete and lowrelevance results This study presents an automated patent retrieval framework integrating Large Language Models LLMs with Retri…

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
Xubin Yue, Zhenhua Xu, Wenpeng Xing, Jiahui Yu, Mohan Li, Meng Han
https://arxiv.org/abs/2509.00918

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
Addressing the intellectual property protection challenges in commercial deployment of large language models (LLMs), existing black-box fingerprinting techniques face dual challenges from incremental fine-tuning erasure and feature-space defense due to their reliance on overfitting high-perplexity trigger patterns. Recent work has revealed that model editing in the fingerprinting domain offers distinct advantages, including significantly lower false positive rates, enhanced harmlessness, and su…

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
Zhenhua Xu, Zhaokun Yan, Binhan Xu, Xin Tong, Haitao Xu, Yourong Chen, Meng Han
https://arxiv.org/abs/2509.00820

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
With the rapid advancement of large language models (LLMs), safeguarding intellectual property (IP) has become increasingly critical. To address the challenges of high costs and potential contamination in fingerprint integration, we propose LoRA-FP, a lightweight, plug-and-play framework that embeds backdoor fingerprints into LoRA adapters through constrained fine-tuning. This design enables seamless fingerprint transplantation via parameter fusion, eliminating the need for full-parameter updat…

gMBA: Expression Semantic Guided Mixed Boolean-Arithmetic Deobfuscation Using Transformer Architectures
Youjeong Noh, Joon-Young Paik, Jingun Kwon, Eun-Sun Cho
https://arxiv.org/abs/2506.23634

gMBA: Expression Semantic Guided Mixed Boolean-Arithmetic Deobfuscation Using Transformer Architectures
Mixed Boolean-Arithmetic (MBA) obfuscation protects intellectual property by converting programs into forms that are more complex to analyze. However, MBA has been increasingly exploited by malware developers to evade detection and cause significant real-world problems. Traditional MBA deobfuscation methods often consider these expressions as part of a black box and overlook their internal semantic information. To bridge this gap, we propose a truth table, which is an automatically constructed …

I Stolenly Swear That I Am Up to (No) Good: Design and Evaluation of Model Stealing Attacks
Daryna Oliynyk, Rudolf Mayer, Kathrin Grosse, Andreas Rauber
https://arxiv.org/abs/2508.21654

I Stolenly Swear That I Am Up to (No) Good: Design and Evaluation of Model Stealing Attacks
Model stealing attacks endanger the confidentiality of machine learning models offered as a service. Although these models are kept secret, a malicious party can query a model to label data samples and train their own substitute model, violating intellectual property. While novel attacks in the field are continually being published, their design and evaluations are not standardised, making it challenging to compare prior works and assess progress in the field. This paper is the first to address…

Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution
Zhicheng Zhang, Peizhuo Lv, Mengke Wan, Jiang Fang, Diandian Guo, Yezeng Chen, Yinlong Liu, Wei Ma, Jiyan Sun, Liru Geng
https://arxiv.org/abs/2507.20650

Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution
Recently, Deep Learning (DL) models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property (IP) risks, as models are distributed on numerous local devices, making them vulnerable to theft and redistribution. Most existing ownership protection solutions (e.g., backdoor-based watermarking) are designed for cloud-based AI-as-a-Service (AIaaS) and are not directly applicab…

SoK: Large Language Model Copyright Auditing via Fingerprinting
Shuo Shao, Yiming Li, Yu He, Hongwei Yao, Wenyuan Yang, Dacheng Tao, Zhan Qin
https://arxiv.org/abs/2508.19843 ht…

SoK: Large Language Model Copyright Auditing via Fingerprinting
The broad capabilities and substantial resources required to train Large Language Models (LLMs) make them valuable intellectual property, yet they remain vulnerable to copyright infringement, such as unauthorized use and model theft. LLM fingerprinting, a non-intrusive technique that extracts and compares the distinctive features from LLMs to identify infringements, offers a promising solution to copyright auditing. However, its reliability remains uncertain due to the prevalence of diverse mod…

NWaaS: Nonintrusive Watermarking as a Service for X-to-Image DNN
Haonan An, Guang Hua, Yu Guo, Hangcheng Cao, Susanto Rahardja, Yuguang Fang
https://arxiv.org/abs/2507.18036 htt…

NWaaS: Nonintrusive Watermarking as a Service for X-to-Image DNN
The intellectual property of deep neural network (DNN) models can be protected with DNN watermarking, which embeds copyright watermarks into model parameters (white-box), model behavior (black-box), or model outputs (box-free), and the watermarks can be subsequently extracted to verify model ownership or detect model theft. Despite recent advances, these existing methods are inherently intrusive, as they either modify the model parameters or alter the structure. This natural intrusiveness raise…

Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering
Haonan An, Guang Hua, Hangcheng Cao, Zhengru Fang, Guowen Xu, Susanto Rahardja, Yuguang Fang
https://arxiv.org/abs/2507.18034

Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering
The intellectual property of deep generative networks (GNets) can be protected using a cascaded hiding network (HNet) which embeds watermarks (or marks) into GNet outputs, known as box-free watermarking. Although both GNet and HNet are encapsulated in a black box (called operation network, or ONet), with only the generated and marked outputs from HNet being released to end users and deemed secure, in this paper, we reveal an overlooked vulnerability in such systems. Specifically, we show that t…

Side-Channel Extraction of Dataflow AI Accelerator Hardware Parameters
Guillaume Lomet, Ruben Salvador, Brice Colombier, Vincent Grosso, Olivier Sentieys, Cedric Killian
https://arxiv.org/abs/2506.15432

Side-Channel Extraction of Dataflow AI Accelerator Hardware Parameters
Dataflow neural network accelerators efficiently process AI tasks on FPGAs, with deployment simplified by ready-to-use frameworks and pre-trained models. However, this convenience makes them vulnerable to malicious actors seeking to reverse engineer valuable Intellectual Property (IP) through Side-Channel Attacks (SCA). This paper proposes a methodology to recover the hardware configuration of dataflow accelerators generated with the FINN framework. Through unsupervised dimensionality reduction…

MEraser: An Effective Fingerprint Erasure Approach for Large Language Models
Jingxuan Zhang, Zhenhua Xu, Rui Hu, Wenpeng Xing, Xuhong Zhang, Meng Han
https://arxiv.org/abs/2506.12551

MEraser: An Effective Fingerprint Erasure Approach for Large Language Models
Large Language Models (LLMs) have become increasingly prevalent across various sectors, raising critical concerns about model ownership and intellectual property protection. Although backdoor-based fingerprinting has emerged as a promising solution for model authentication, effective attacks for removing these fingerprints remain largely unexplored. Therefore, we present Mismatched Eraser (MEraser), a novel method for effectively removing backdoor-based fingerprints from LLMs while maintaining …