paper-with-me

홈 › Papers

On the Vulnerability of Parameter-Level Defenses to Model Merging

2026-06-29 · Kuangpu Guo, Qingyan Zheng, Jian Liang, Yongcan Yu, Zilei Wang, Ran He, Tieniu Tan arxiv

The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized models without authorization. Recent works propose parameter-level defenses that employ linear parameter transformations to neutralize this threat. In this paper, we systematically analyze such defenses and reveal that their protected task vectors are inherently small in magnitude. Consequently, the protected weights remain overwhelmingly dominated by the pretrained model. Based on this observation, we designate the pretrained model as a static reference anchor and propose the Anchor-Guided Attack (AGA) to circumvent existing safeguards. Specifically, AGA aligns the protected model with this anchor to recover the transformation matrix analytically. Extensive evaluations validate that AGA consistently bypasses both individual and composite defenses under realistic defense-agnostic scenarios. Furthermore, we provide Anchor-Repulsive Fine-tuning (ARF), a defense method to mitigate the anchor dominance leveraged by AGA. Empirical results confirm that ARF effectively defeats the proposed attack. Our code is available at https://github.com/krumpguo/secure-merge-attack.

📄 PDF Abstract BibTeX arXiv:2606.30360

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures

2024-10-28 · Victoria Benjamin, Emily Braca, Israel Carter, Hafsa Kanchwala 외

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 1…

Misinformation

Rethinking IC layout vulnerability: Simulation-based hardware Trojan threat assessment with high fidelity

2024-05-19 · IEEE Symposium on Security and Privacy (SP) 2024 5 · Xinming Wei, Jiaxi Zhang, Guojie Luo

Due to the escalating complexity of chip design and the exorbitant cost of building cutting-edge manufacturing facilities, outsourcing the fabrication of Integrated Circuits (ICs) is prevalent in modern semiconductor ind…

Side Channel Analysis

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks

2026-02-16 · Lukas Struppek, Adam Gleave, Kellin Pelrine arxiv

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must primarily depend on internal s…

Adversarial Robustness for Machine Learning Cyber Defenses Using Log Data

2020-07-29 · Kai Steverson, Jonathan Mullin, Metin Ahiskali

There has been considerable and growing interest in applying machine learning for cyber defenses. One promising approach has been to apply natural language processing techniques to analyze logs data for suspicious behavi…

Adversarial AttackAdversarial RobustnessBIG-bench Machine LearningDeep Reinforcement Learning

EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations

2025-12-01 · Xinyun Zhou, Xinfeng Li, Yinan Peng, Ming Xu 외 arxiv

Retrieval-Augmented Generation (RAG) systems are increasingly central to robust AI, enhancing large language model (LLM) faithfulness by incorporating external knowledge. However, our study unveils a critical, overlooked…