Fan Li

This paper surveys how integrating Edge Computing, Machine Learning, and Deep Learning can enhance the security and resilience of complex Internet of Vehicles (IoV) networks.

AgentVisor is a novel defense framework that uses semantic virtualization, inspired by OS principles, to significantly reduce LLM agent vulnerability to prompt injection while maintaining high utility.

The paper introduces MGTEVAL, a comprehensive and extensible platform designed to systematically evaluate the performance, robustness, and efficiency of machine-generated text detectors.

The paper proposes REACT, an adversarial training framework that significantly enhances the robustness and few-shot performance of machine-generated text detection by having a Retrieval-Augmented Generation (RAG)-powered attacker co-evolve with the detector.

The paper introduces SADBench, a systematic benchmark designed to evaluate both the effectiveness of steganographic attacks injecting harmful content and the robustness of steganalysis defenses against these threats.

The paper systematically measures the risk of current image-to-3D models generating harmful geometries, finding that these models are effective at reconstruction and existing safeguards are insufficient.

The paper proposes a universal graph backdoor defense framework that addresses feature-based graph backdoor attacks, which are more challenging than traditional subgraph-based attacks, by leveraging local feature consistency.

The paper introduces MARS, a novel meta-adversarial framework that significantly improves black-box adversarial attacks against state-of-the-art Singing Voice Deepfake Detection (SVDD) systems by escaping the Linearity Trap.

The paper introduces extsc{Ptah}, a multi-agent harness designed to improve verifiable multimodal deep research by orchestrating the entire report generation process, ensuring factual grounding and visual consistency.

The paper proposes a novel four-stage simulation framework that uses GPS-derived seasonal spatial priors and LLMs to generate demographically accurate, synthetic tourist mobility schedules for urban planning.

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.

The paper introduces a novel Clean-Referenced Feature-Vocoder Attack, a black-box adversarial attack that perturbs high-level SSL feature representations instead of raw audio waveforms, achieving superior transferability and robustness against modern ASR defenses.