collaborators

7 papers

cs.CR2026

Twin Agent: Context Residual Compression for Privilege Separated Agents

Zhanhao Hu, Dennis Jacob, Xiao Huang +3

Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Exist…

cs.RO2026

Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies

Zi Yin, Peilin Chai, Siyuan Huang +1

Diffusion-based action generation has become a foundational component of embodied AI, but its reliance on visual conditioning leaves deployed visuomotor policies vulnerable to adve…

cs.CL2026

GradShield: Alignment Preserving Finetuning

Zhanhao Hu, Xiao Huang, Patrick Mendoza +4

Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implicitly harmful data. Even some…

cs.CR2026

Preventing Prompt Injection with Type-Directed Privilege Separation

Dennis Jacob, Emad Alghamdi, Zhanhao Hu +2

Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security co…

cs.LG2026

JULI: Jailbreak Large Language Models by Self-Introspection

Jesson Wang, Zhanhao Hu, David Wagner

Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-align…

cs.CR2025

JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift

Julien Piet, Xiao Huang, Dennis Jacob +7

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulne…