Skip to content

Author

Shuchao Pang

We have 6 of 21 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.

Book Open access Nov 2026

DIRE: Dual-grained Internal Refusal Estimation for VLM Jailbreak Detection

While Vision-Language Models (VLMs) excel at multimodal tasks, they are increasingly vulnerable to sophisticated multimodal jailbreak attacks. Conventional defenses typically introduce significant training overhead, risk degrading model capabilities, or cause severe inference latency via external modules. Additionally,...

Xi-Yu Zeng, Li-Ming Lu, Xu Zheng et al. · 0 citations
#small language model Book Open access Nov 2026

DIRE: Dual-grained Internal Refusal Estimation for VLM Jailbreak Detection

Dual-grained Internal Refusal Estimation (DIRE), a training-free detection framework that jointly probes resilient Attention routing and FFN semantic memory within effective semantic layers to detect multimodal jailbreaks in a training-free manner, is introduced.

Xi-Yu Zeng, Li-Ming Lu, Xu Zheng et al. · 0 citations
Preprint Sep 2026

SteerProbe: Learning to Bypass Safety Steering in Vision-Language Models

Activation steering offers an inference-time defense for vision--language models (VLMs) by modifying intermediate representations without updating backbone parameters. However, protection on benchmark inputs may not persist across alternative expressions of the same harmful request. We investigate this gap using fixed...

Xin-Wei Zhang, Ao-Ting Hu, Hang-Cheng Liu et al. · 0 citations
2026

SafeSteer: Adaptive Subspace Steering for Efficient Jailbreak Defense in Vision Language Models

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the model’s utility; and (2) many defense mechanisms significantly reduce the model’...

Shu-Chao Pang, Xiyu Zeng, Si-Yuan Liang et al. · 6 citations
Sep 2025

SafeSteer: Adaptive Subspace Steering for Efficient Jailbreak Defense in Vision-Language Models

SafeSteer is a lightweight, inference-time steering framework that effectively defends against diverse jailbreak attacks without modifying model weights, using the innovative use of Singular Value Decomposition to construct a low-dimensional safety subspace during inference.

Xiyu Zeng, Siyuan Liang, Liming Lu et al. · 0 citations
#artificial intelligence Review Aug 2026

AI Alignment through a Game-theoretic Lens: A Survey

This perspective clarifies where current alignment methods genuinely benefit from game-theoretic analysis, where the framework is looser, and what challenges remain in building robust, adaptive, and verifiable AI systems.

Yaxin Cai, Zhong-Rui Zhao, Zhi-Gang Lu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.