Author

Sheng-Yuan Pang

h-index 3 View on Semantic Scholar

We have 3 of 10 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

MMA-SafetyBench: A Benchmark for Multimodal Agent Safety Evaluation

Multimodal agents increasingly rely on visual interfaces to perceive state and select actions, creating an attack surface not captured by text-only safety evaluations. We study Visual Semantic Hijacking, in which deceptive but semantically meaningful interface elements, such as forged system alerts, cause an agent to d...

Yu-Ke Wang, Ben-Lei Cui, Sheng-Yuan Pang et al. · 0 citations

Review Aug 2026

Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models

Results reveal a systemic vulnerability of frontier VLMs to meta-adaptive jailbreaks to meta-adaptive jailbreaks and motivate defenses against meta-level adversaries.

Ben-Lei Cui, Sheng-Yuan Pang, Yu-Ke Wang et al. · 1 citation

2026

Patronus: Safeguarding Text-to-Image Models Against Adversarial Fine-Tuning

Text-to-image (T2I) models can be exploited to produce unsafe images. Existing safety measures, e.g., content moderation or model alignment, can be weakened by adversaries who attempt to restore unsafe generation through model fine-tuning. This paper presents Patronus, a defensive framework that improves T2I models’ re...

Xin-Feng Li, Sheng-Yuan Pang, Jialin Wu et al. · IEEE Transactions on Informa... · 0 citations