LLMに対するポイズニング攻撃
本記事では、LLMに対するポイズニング攻撃の最新動向について解説します。LLMに対するポイズニング攻撃の特徴や攻撃方法について概観し、その後主要な防御技術の概要や課題、今後の展望について説明します。
Lexo: Eliminating Stealthy Supply-Chain Attacks via LLM-Assisted Program Regeneration
Authors: Evangelos Lamprou, Julian Dai, Grigoris Ntousakis, Martin C. Rinard, Nikos Vasilakis | Published: 2025-10-16
Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
Authors: Andrew Zhao, Reshmi Ghosh, Vitor Carvalho, Emily Lawton, Keegan Hines, Gao Huang, Jack W. Stokes | Published: 2025-10-16
Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
Authors: Mason Nakamura, Abhinav Kumar, Saaduddin Mahmud, Sahar Abdelnabi, Shlomo Zilberstein, Eugene Bagdasarian | Published: 2025-10-16
RHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics and Techniques with Large Language Models
Authors: Fanchao Meng, Jiaping Gui, Yunbo Li, Yue Wu | Published: 2025-10-16
In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers
Authors: Avihay Cohen | Published: 2025-10-15
Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
Authors: Xin Zhao, Xiaojun Chen, Bingshan Liu, Haoyu Gao, Zhendong Zhao, Yilong Chen | Published: 2025-10-15
Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
Authors: Li Bai, Qingqing Ye, Xinwei Zhang, Sen Zhang, Zi Liang, Jianliang Xu, Haibo Hu | Published: 2025-10-15
Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
Authors: Baogang Song, Dongdong Zhao, Jianwen Xiang, Qiben Xu, Zizhuo Yu | Published: 2025-10-15
Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems
Authors: Jiaxin Gao, Chen Chen, Yanwen Jia, Xueluan Gong, Kwok-Yan Lam, Qian Wang | Published: 2025-10-14