Hao Pan

MANA introduces an agentic multimodal reasoning framework that significantly improves the efficiency and accuracy of detecting mobile advertisements by integrating multiple types of signals into a guided UI navigation strategy.

PrismWF introduces a multi-granularity patch-based Transformer to significantly improve website fingerprinting attacks by effectively modeling complex, mixed-traffic patterns from multi-tab browsing sessions.

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.

The paper proposes 'inertial mining,' a novel protocol that ensures miners follow the intended Bitcoin rules by making the protocol an economic equilibrium, thereby preventing profitable deviations like selfish mining.

The paper introduces SafeRedirect, a system-level defense that prevents frontier LLMs from generating harmful content during legitimate tasks that structurally require it, significantly reducing unsafe generation rates.

The paper proposes COSE, a method that uses an LLM's intrinsic confidence as an uncertainty signal to improve self-evolutionary training, achieving state-of-the-art performance on general reasoning and mathematics.