8 papers
LLMs Can Unlearn Refusal with Only 1,000 Benign Samples
Yangyang Guo, Ziwei Xu, Si Liu +2
This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with…
Involuntary Jailbreak: On Self-Prompting Attacks
Yangyang Guo, Yangyan Li, Mohan Kankanhalli
In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term \textbf{involuntary jailbreak}. Unlike existing jailbreak attacks, this weakn…
FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed
Sizhe Dang, Yangyang Guo, Yanjun Zhao +4
Fine-tuning large language models (LLMs) often faces GPU memory bottlenecks: the backward pass of first-order optimizers like Adam increases memory usage to more than 10 times the…
Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
Yang Guo, Yutian Tao, Yifei Ming +2
Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostl…
VidLBEval: Benchmarking and Mitigating Language Bias in Video-Involved LVLMs
Yiming Yang, Yangyang Guo, Hui Lu +1
Recently, Large Vision-Language Models (LVLMs) have made significant strides across diverse multimodal tasks and benchmarks. This paper reveals a largely under-explored problem fro…
Technical Report for ICML 2024 TiFA Workshop MLLM Attack Challenge: Suffix Injection and Projected Gradient Descent Can Easily Fool An MLLM
Yangyang Guo, Ziwei Xu, Xilie Xu +3
This technical report introduces our top-ranked solution that employs two approaches, \ie suffix injection and projected gradient descent (PGD) , to address the TiFA workshop MLLM…