When Safety Detectors Aren’t Enough: A Stealthy and Effective Jailbreak Attack on LLMs via Steganographic Techniques
Authors: Jianing Geng, Biao Yi, Zekun Fei, Tongxi Wu, Lihai Nie, Zheli Liu | Published: 2025-05-22
透かし除去技術
From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
Authors: Yidan Wang, Yubing Ren, Yanan Cao, Binxing Fang | Published: 2025-05-15
Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
Authors: Yijie Xu, Aiwei Liu, Xuming Hu, Lijie Wen, Hui Xiong | Published: 2025-03-06 | Updated: 2025-03-15
Neural Network Laundering: Removing Black-Box Backdoor Watermarks from Deep Neural Networks
Authors: William Aiken, Hyoungshick Kim, Simon Woo | Published: 2020-04-22