5 papers
R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models
Ziming Zhang, Li Li, Guorui Feng +2
Large language models (LLMs) are widely deployed in multiple scenarios due to reasoning capabilities. In order to prevent the models from being misused, watermarking is generally e…
Trigger Where It Hurts: Unveiling Hidden Backdoors through Sensitivity with Sensitron
Gejian Zhao, Hanzhou Wu, Xinpeng Zhang
Backdoor attacks pose a significant security threat to natural language processing (NLP) systems, but existing methods lack explainable trigger mechanisms and fail to quantitativel…
Yet Another Watermark for Large Language Models
Siyuan Bao, Ying Shi, Zhiguang Yang +2
Existing watermarking methods for large language models (LLMs) mainly embed watermark by adjusting the token sampling prediction or post-processing, lacking intrinsic coupling with…
RFNNS: Robust Fixed Neural Network Steganography with Universal Text-to-Image Models
Yu Cheng, Jiuan Zhou, Jiawei Chen +2
With the rapid development of generative AI, image steganography has garnered widespread attention due to its unique concealment. Recent studies have demonstrated the practical adv…
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
Gejian Zhao, Hanzhou Wu, Xinpeng Zhang +1
Chain-of-Thought (CoT) enhances an LLM's ability to perform complex reasoning tasks, but it also introduces new security issues. In this work, we present ShadowCoT, a novel backdoo…