Hui Xue

The paper introduces AgentRAE, a novel backdoor attack that successfully forces mobile GUI agents to execute remote actions using visually natural triggers found in system notifications, achieving high success rates while remaining difficult to detect.

This paper provides the first integrated analysis of model dememorization, unifying unlearnability and unlearning methods, and offering theoretical guarantees on dememorization depth.

The paper proposes a black-box attack using a hierarchical genetic algorithm to induce 'overthinking' in Large Reasoning Models, demonstrating that this vulnerability can cause significant resource exhaustion.

The paper quantifies the exact parametric memory capacity of LLMs using LoRA and proposes a new optimization strategy, MemFT, to enhance memory fidelity.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

The paper introduces ConsisGuard, a framework that addresses the 'deliberation-to-enforcement gap' in LLM guardrails by ensuring that the reasoning process is faithfully and consistently translated into the final safety decision.

MESA is a targeted alignment framework that decentralizes safety responsibilities across multiple experts in Mixture-of-Experts (MoE) LLMs using Optimal Transport theory, thereby improving safety robustness without sacrificing utility.

MaskForge is a novel, adaptive, black-box attack framework that significantly improves jailbreaking diffusion large language models (dLLMs) by treating red-teaming as an optimized search over reusable structural patterns.