29 citations · 62 across the 27 of their papers we have counts for
9 papers · 1 filter
SIR: Self-improving Red-teaming for Compute Use Agents
Chen Xiong, Zhiyuan He, Pin-Yu Chen +2
Computer-use agents (CUAs) are agents powered by vision-language models (VLMs) that perceive a screen and operate an operating system through mouse, keyboard, and terminal interact…
Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
Chen Xiong, Zhiyuan He, Pin-Yu Chen +2
Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, develope…
Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
Xiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho
As large language models (LLMs) become more integral to society and technology, ensuring their safety becomes essential. Jailbreak attacks exploit vulnerabilities to bypass safety…
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
Lei Hsiung, Tianyu Pang, Yung-Chen Tang +4
Recent advancements in large language models (LLMs) have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. Howe…
Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
Xiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho
Large Language Models (LLMs) are increasingly being integrated into services such as ChatGPT to provide responses to user queries. To mitigate potential harm and prevent misuse, th…
Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
Chen Xiong, Xiangyu Qi, Pin-Yu Chen +1
Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jai…
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
Xiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho
Large Language Models (LLMs) are becoming a prominent generative AI tool, where the user enters a query and the LLM generates an answer. To reduce harm and misuse, efforts have bee…
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang +8
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training. However,…
VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
Sheng-Yen Chou, Pin-Yu Chen, Tsung-Yi Ho
Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many…