3 citations · 5 across the 27 of their papers we have counts for
31 papers
pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation
Zonghao Ying, Xiangfan Wu, Bo Yang +5
Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user authorization. We introduce pik…
CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-based Agents
Xiao Yang, Yangchen Ou, Yuhan Gao +3
Large language model (LLM)-based agents increasingly rely on external tools and content, exposing them to indirect prompt injection (IPI). This threat has motivated a wide range of…
The Missing Boundary: How Autonomous Agents Lose Control
Zonghao Ying, Xiangfan Wu, Bo Yang +5
Autonomous agents increasingly perform long-horizon tasks involving tool use, persistent state, and consequential actions, raising a fundamental question: \emph{under what conditio…
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…
Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection
Zonghao Ying, Xiangfan Wu, Huiyu Wu +4
We assess indirect prompt injection in DeepSeek Harness (DSH), using AI-Infra-Guard (A.I.G) to construct tests, deliver controlled taint, execute DSH, collect traces, and judge out…
Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs
Xiangfan Wu, Zonghao Ying, Huiyu Wu +4
As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the ecosystem. Auditing the quality o…
Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding
Yisong Xiao, Aishan Liu, Yongxin Huang +6
Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resultin…
SkillJack: Persistent Skill Backdoors in Self-Evolving Agents
Zonghao Ying, Xiangfan Wu, Huiyu Wu +4
Self-evolving agents increasingly convert interaction histories into reusable skills that persist beyond individual tasks. While prior work studies memory and retrieval poisoning,…
SkillSentry: Adaptive Honey Worlds for Dynamic Safety Testing of Agent Skills
Nizhang Li, Zonghao Ying, Xiangfan Wu +7
External skills extend the capabilities of large language model agents, but also introduce an execution-time attack surface: a skill that appears benign under inspection may reveal…
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
Haowen Dai, Zonghao Ying, Wenfeng Li +10
Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective c…
SafeGen: Goal-Conditioned Video Diffusion of Safety-Critical Scenarios for VLM-Based Autonomous Driving
Jiangfan Liu, Zexuan Cui, Tianyuan Zhang +7
VLMs are increasingly deployed in AD systems, creating an urgent need for rigorous safety evaluation under rare yet safety-critical scenarios. Among these, interactions with vulner…
Technical Report on the CVPR 2026@AdvML Workshop Challenge
Tianyuan Zhang, Zonglei Jing, Jiangfan Liu +47
Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Cha…
Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
Yong Yang, Xing Zheng, Huiyu Wu +7
The fast growth of open-source AI infrastructure, from model serving engines and agent platforms to the Model Context Protocol (MCP) ecosystem and the language models themselves, h…
GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic
Tianyuan Zhang, Peng Yue, Zihao Peng +8
Multimodal large language models (MLLMs) are increasingly integrated into autonomous driving (AD) systems; however, they remain vulnerable to diverse safety threats, particularly i…
Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw
Zonghao Ying, Xiao Yang, Siyang Wu +7
The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI sy…
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…
Uncovering Strategic Egoism Behaviors in Large Language Models
Yaoyuan Zhang, Aishan Liu, Zonghao Ying +4
Large language models (LLMs) face growing trustworthiness concerns (\eg, deception), which hinder their safe deployment in high-stakes decision-making scenarios. In this paper, we…
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…
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…
Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
Yisong Xiao, Aishan Liu, Siyuan Liang +3
Large Language Models (LLMs) have demonstrated impressive performance across various tasks, yet they remain vulnerable to generating toxic content, necessitating detoxification str…
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
Zonghao Ying, Siyang Wu, Run Hao +44
Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks…
PRJ: Perception-Retrieval-Judgement for Generated Images
Qiang Fu, Zonglei Jing, Zonghao Ying +1
The rapid progress of generative AI has enabled remarkable creative capabilities, yet it also raises urgent concerns regarding the safety of AI-generated visual content in real-wor…
AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
Zonghao Ying, Le Wang, Yisong Xiao +7
The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands,…
Manipulating Multimodal Agents via Cross-Modal Prompt Injection
Le Wang, Zonghao Ying, Tianyuan Zhang +5
The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to bett…