works on

From the 1 of 13 linked papers with an AI index.

collaborators

13 papers

cs.CR2026

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…

cs.CV2026

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…

cs.CV2026

Technical Report on the CVPR 2026@AdvML Workshop Challenge

Tianyuan Zhang, Zonglei Jing, Jiangfan Liu +47

The paper reports on the CVPR 2026@AdvML Workshop Challenge, which evaluated adversarial attacks on multimodal vision‑language agents for autonomous driving using multi‑view visual…

cs.CV2026

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,…

cs.CV2026

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…

cs.CL2026

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…