most citedDemystifying LLM Supply Chain Vulnerabilities in the Wild: Distribution, Root Cause, and Real-World Impact

1 citations · 1 across the 3 of their papers we have counts for

collaborators

9 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.CR20261 cited

Demystifying LLM Supply Chain Vulnerabilities in the Wild: Distribution, Root Cause, and Real-World Impact

Shenao Wang, Yanjie Zhao, Zhao Liu +2

LLMs are rapidly transitioning from research prototypes to core components in production systems across industries such as finance and healthcare. These deployments rely on a growi…

cs.AI2026

ElephantAgent: Contextual State Continuity in Agentic Systems

Jiankai Jin, Xiangzheng Zhang, Zhao Liu +4

Agentic systems enhance their capabilities by invoking external tools and maintaining persistent memory. However, these external dependencies introduce novel attack surfaces. Recen…

cs.LG2026

Robust Privacy: Inference-Stage Privacy through Certified Robustness

Jiankai Jin, Xiangzheng Zhang, Zhao Liu +4

An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives of the model's training data. The infe…

cs.CR2026

Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions

Shenao Wang, Xinyi Hou, Zhao Liu +5

GitHub Actions is increasingly used to deploy LLM-based agents for repository-centric tasks such as issue triage, pull-request review, code modification, and release assistance. Th…

cs.CR2026

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…