collaborators

15 papers

cs.AI2026

Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models

Dongdong Yang, Deyue Zhang, Zhao Liu +5

Text-to-Image (T2I) generative models have achieved remarkable progress in synthesizing high-quality visual content, yet they remain vulnerable to adversarial misuse, particularly…

cs.CR2026

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

Zhe Liu, Zonghao Ying, Wenxin Zhang +5

Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilit…

cs.CR2026

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs

Wenzhuo Xu, Zhipeng Wei, Zonghao Ying +4

Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-image inputs, inadvertently in…

cs.CV2026

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models

Zhiqiang Wang, Dongrui Liu, Yan Li +4

Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the sa…

cs.LG2026

Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News Detection

Weilin Zhou, Zonghao Ying, Rongchen Zhao +7

Prevalent multimodal fake news detection relies on consistency-based fusion, yet this paradigm fundamentally misinterprets critical cross-modal discrepancies as noise, leading to o…

cs.CV2026

TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks

Quanchen Zou, Nizhang Li, Wenxin Zhang +4

Text-to-Video (T2V) models have demonstrated remarkable capability in generating temporally coherent videos from natural language prompts, yet they also risk producing unsafe conte…