3 citations · 7 across the 7 of their papers we have counts for
8 papers
Red-TTT: Test-Time Training for Automated Jailbreaking Large Language Models
Tongyan Hu, Hao Li, Xiaogeng Liu +8
Large language models remain vulnerable to jailbreaks, and automated red teaming is the standard way to find jailbreaks in large language models at scale. Current methods either dr…
Decomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services
Bowen Sun, Zhengyue Zhao, Xiaogeng Liu +2
Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attacks exploit this limitation by splitting…
Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
Zhengyuan Jiang, Yuepeng Hu, Yuchen Yang +2
Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often adde…
AdaProb: Efficient Machine Unlearning via Adaptive Probability
Zihao Zhao, Yuchen Yang, Anjalie Field +1
Machine unlearning, enabling a trained model to forget specific data, is crucial for addressing erroneous data and adhering to privacy regulations like the General Data Protection…
RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning
Zihao Zhao, Yuchen Yang, Yijiang Li +1
The ripple effect poses a significant challenge in knowledge editing for large language models. Namely, when a single fact is edited, the model struggles to accurately update the r…
Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models
Yuchen Yang, Kwonjoon Lee, Behzad Dariush +2
Video Anomaly Detection (VAD) is crucial for applications such as security surveillance and autonomous driving. However, existing VAD methods provide little rationale behind detect…
PLeak: Prompt Leaking Attacks against Large Language Model Applications
Bo Hui, Haolin Yuan, Neil Gong +2
Large Language Models (LLMs) enable a new ecosystem with many downstream applications, called LLM applications, with different natural language processing tasks. The functionality…
SneakyPrompt: Jailbreaking Text-to-image Generative Models
Yuchen Yang, Bo Hui, Haolin Yuan +2
Text-to-image generative models such as Stable Diffusion and DALLE raise many ethical concerns due to the generation of harmful images such as Not-Safe-for-Work (NSFW) ones.…