SymSan: Mitigating Malware Embedding in Large Language Models via Parameter Space Symmetry
Ming Tan, Wei Li, Tao Hu, Qian Chen, Aodi Liu, Hailong Ma
2026年份
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper，每个回答都会注明依据哪几篇。
相关 Paper
- Logit Laundering: Evading Data-Use Auditing in Large Language ModelsRuihan Hu, Wei Luo, Yu-Ming Shang, Jiakai Wang 等CCS 2026
- Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding SpaceLeo Schwinn, David Dobre, Sophie Xhonneux, Gauthier Gidel 等NeurIPS 2024 · 被引用 113 次
- A Watermark for Large Language ModelsJohn Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz 等ICML 2023 · 被引用 854 次
- Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code ObfuscationSeyedreza Mohseni, Seyedali Mohammadi, Deepa Tilwani, Yash Saxena 等AAAI 2025 · 被引用 6 次
- A Semantic Invariant Robust Watermark for Large Language ModelsAiwei Liu, Leyi Pan, Xuming Hu, Shiao Meng 等ICLR 2024 · 被引用 108 次
