2 citations · 2 across the 20 of their papers we have counts for
20 papers
Delegated Misalignment: How Multi-Agent Structures Amplify LLM Safety Risks
Zonghao Ying, Jiaqi Yan, Huize Luo +3
Large language models (LLMs) are increasingly deployed in multi-agent systems where a principal agent decomposes tasks and delegates them to subordinate agents that may invoke exte…
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…
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…
AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
Zonghao Ying, Haozheng Wang, Jiangfan Liu +5
Large Language Model (LLM) agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe secu…
Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models
Zonghao Ying, Haowen Dai, Lianyu Hu +5
Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and formalize the inscriptive jailbreak,…
Evolving Deception: When Agents Evolve, Deception Wins
Zonghao Ying, Haowen Dai, Tianyuan Zhang +6
Self-evolving agents offer a promising path toward scalable autonomy. However, in this work, we show that in competitive environments, self-evolution can instead give rise to a ser…
Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking
Moyang Chen, Zonghao Ying, Wenzhuo Xu +4
Recent text-to-video (T2V) models can synthesize complex videos from lightweight natural language prompts, raising urgent concerns about safety alignment in the event of misuse in…
DIVER: Dynamic Iterative Visual Evidence Reasoning for Multimodal Fake News Detection
Weilin Zhou, Zonghao Ying, Chunlei Meng +6
Multimodal fake news detection is crucial for mitigating adversarial misinformation. Existing methods, relying on static fusion or LLMs, face computational redundancy and hallucina…
SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization
Xinghao Wang, Changtao Miao, Dianmo Sheng +6
Malicious image manipulation threatens public safety and requires efficient localization methods. Existing approaches depend on costly pixel-level annotations which make training e…
RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
Le Wang, Zonghao Ying, Xiao Yang +7
Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that m…
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…
SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge
Zonghao Ying, Moyang Chen, Nizhang Li +6
Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obv…
Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling
Deyue Zhang, Dongdong Yang, Junjie Mu +6
Multimodal large language models (MLLMs) exhibit remarkable capabilities but remain susceptible to jailbreak attacks exploiting cross-modal vulnerabilities. In this work, we introd…
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Zonghao Ying, Yangguang Shao, Jianle Gan +8
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face…
Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
Junjie Mu, Zonghao Ying, Zhekui Fan +6
Jailbreak attacks on Large Language Models (LLMs) have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses that they are d…
PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
Quanchen Zou, Zonghao Ying, Moyang Chen +7
The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation…
Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
Zonghao Ying, Guangyi Zheng, Yongxin Huang +6
This study presents the first comprehensive safety evaluation of the DeepSeek models, focusing on evaluating the safety risks associated with their generated content. Our evaluatio…
Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
Zonghao Ying, Deyue Zhang, Zonglei Jing +7
Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. Howev…
Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application
Wenzhuo Xu, Zhipeng Wei, Xiongtao Sun +5
Recently, Multimodal Large Language Models (MLLMs) have demonstrated their superior ability in understanding multimodal content. However, they remain vulnerable to jailbreak attack…
Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles
Xiongtao Sun, Deyue Zhang, Dongdong Yang +2
Large language models (LLMs) have significantly enhanced the performance of numerous applications, from intelligent conversations to text generation. However, their inherent securi…