30 citations · 133 across the 49 of their papers we have counts for
6 papers · 1 filter
TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling
Ling Zhou, Yihao Huang, Jingling Sun +4
Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and image-based jailbreaks, video ja…
QuISE: Defense against Typographic Attacks on VLMs via Query-Irrelevant Semantic Editing
Shubin Lu, Jiaqi Yin, Yihao Huang
Typographic attacks pose a critical threat to vision-language models (VLMs) by injecting misleading text into images and causing models to rely on adversarial textual cues rather t…
ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization
Hujian Zhu, Yihao Huang, Felix Juefei-Xu +5
Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift jailbreaks have recently em…
Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models
Dongdong An, Pengjie Zhao, Yihao Huang +5
Recent Vision-Language-Action (VLA) models achieve promising performance in robotic manipulation, typically measured by success rates aggregated over predefined object configuratio…
Clarity Is Not Assumed: Understanding LLM-Based Code Generation under Ambiguous Requirements
Di Yang, Xinou Xie, Xiuwen Yang +7
Software requirement ambiguity is ubiquitous in real-world development, stemming from the inherent imprecision of natural language and the varying interpretations of stakeholders.…
Verify Claimed Text-to-Image Models via Boundary-Aware Prompt Optimization
Zidong Zhao, Yihao Huang, Qing Guo +5
As Text-to-Image (T2I) generation becomes widespread, third-party platforms increasingly integrate multiple model APIs for convenient image creation. However, false claims of using…