Yuan Chen

This study empirically analyzed 1,000 Android apps, finding that privacy policies are often vague and frequently fail to align with the actual sensitive data logged by the applications.

The paper introduces RAVEN, a Retrieval-Augmented Vulnerability Exploration Network, which uses LLM agents and RAG to automatically generate comprehensive, structured vulnerability analysis reports for vulnerable code.

The paper introduces a semantics-first verification framework for an implemented Shor oracle for ECDLP in Qrisp, demonstrating that even seemingly correct implementations can fail due to subtle control law violations.

The PopQuiz Attack is a novel black-box membership inference attack that successfully tests whether large language models memorize specific training data by framing the target data as multiple-choice quiz questions.

The paper proposes RADAR, a novel graph-based framework that dynamically defends Retrieval-Augmented Generation (RAG) systems against evolving adversarial attacks while minimizing storage overhead.

The paper introduces SafeMed-R1, a clinically audited LLM that significantly improves safety and ethical alignment for medical applications, matching or exceeding resident performance on safety-critical tasks.

The paper proposes Agentic ASR, a closed-loop framework that treats ASR as a multi-turn refinement task, significantly improving semantic accuracy over traditional token-level metrics.

The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a pervasive issue across current systems.

The paper introduces and demonstrates that leveraging dynamic symmetry—the uniformity of attainable center-of-mass accelerations—significantly enhances a robot's agility, robustness, and multifunctionality across various challenging environments.

This paper analyzes the x402 payment protocol, revealing critical synchronization and security flaws that allow attackers to exploit payment systems and force merchants to subsidize compute costs.

This paper analyzes the x402 payment protocol, revealing systemic vulnerabilities in state synchronization and signature design that allow attackers to exploit payment systems for resource leakage in the AI economy.

SIRI introduces a self-internalizing reinforcement learning framework that allows LLM agents to autonomously discover and integrate reusable skills directly into their core policy, significantly improving performance on complex tasks without external skill generators.

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.