10 papers
HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models
Fangzhou Chen, Shiji Zhao, Mengyang Wang +4
Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks. Parameter-efficient safety alignment methods based on prompt tuning typically rely on a si…
Improving Safety Alignment via Balanced Direct Preference Optimization
Shiji Zhao, Mengyang Wang, Shukun Xiong +7
With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from…
MoAPT: Mixture of Adversarial Prompt Tuning for Vision-Language Models
Shiji Zhao, Qihui Zhu, Shukun Xiong +7
Large pre-trained Vision Language Models (VLMs) demonstrate excellent generalization capabilities but remain highly susceptible to adversarial examples, posing potential security r…
VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack
Shiji Zhao, Shukun Xiong, Yao Huang +7
Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities. However, more modalities bri…
MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks
Zonglin Wu, Yule Xue, Yaoyao Feng +2
As automated attack techniques rapidly advance, CAPTCHAs remain a critical defense mechanism against malicious bots. However, existing CAPTCHA schemes encompass a diverse range of…
Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
Ranjie Duan, Jiexi Liu, Xiaojun Jia +27
Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, of…