8 papers
AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models
Jiacheng Liang, Tanqiu Jiang, Yuhui Wang +3
This paper presents AutoRAN, the first framework to automate the hijacking of internal safety reasoning in large reasoning models (LRMs). At its core, AutoRAN pioneers an execution…
Self-Destructive Language Model
Yuhui Wang, Rongyi Zhu, Ting Wang
Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. Whi…
Dynamic Token Reweighting for Robust Vision-Language Models
Tanqiu Jiang, Jiacheng Liang, Rongyi Zhu +3
Large vision-language models (VLMs) are highly vulnerable to multimodal jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we pr…
GraphRAG under Fire
Jiacheng Liang, Yuhui Wang, Changjiang Li +4
GraphRAG advances retrieval-augmented generation (RAG) by structuring external knowledge as multi-scale knowledge graphs, enabling language models to integrate both broad context a…
Steering Protein Language Models
Long-Kai Huang, Rongyi Zhu, Bing He +1
Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often…
Self-Improving Model Steering
Rongyi Zhu, Yuhui Wang, Tanqiu Jiang +2
Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering me…