activity
20242026
most citedJPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering

3 citations · 5 across the 7 of their papers we have counts for

collaborators

9 papers

cs.CL2026

The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment

Zhexin Zhang, Yida Lu, Junfeng Fang +8

Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training rem…

cs.CL20251 cited

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity

Shiyao Cui, Xijia Feng, Yingkang Wang +6

Emojis are globally used non-verbal cues in digital communication, and extensive research has examined how large language models (LLMs) understand and utilize emojis across context…

cs.MM20253 cited

JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering

Renmiao Chen, Shiyao Cui, Xuancheng Huang +7

Jailbreak attacks against multimodal large language Models (MLLMs) are a significant research focus. Current research predominantly focuses on maximizing attack success rate (ASR),…

cs.MM2025

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs

Shiyao Cui, Qinglin Zhang, Xuan Ouyang +6

Toxicity detection in multimodal text-image content faces growing challenges, especially with multimodal implicit toxicity, where each modality appears benign on its own but convey…

cs.LG2025

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints

Junxiao Yang, Zhexin Zhang, Shiyao Cui +2

Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs); however, the transferability of these attacks across different models remains limited.…

cs.CL20251 cited

LongSafety: Evaluating Long-Context Safety of Large Language Models

Yida Lu, Jiale Cheng, Zhexin Zhang +7

As Large Language Models (LLMs) continue to advance in understanding and generating long sequences, new safety concerns have been introduced through the long context. However, the…