Ning Wang

This paper analyzes large-scale reasoning traces from LLM-based binary vulnerability analysis, identifying four structured, token-level implicit patterns that govern how LLMs explore code paths.

The paper proposes TriageFuzz, a token-aware fuzzing framework that significantly reduces the number of queries needed to jailbreak LLMs while maintaining high attack success rates.

The paper introduces BFIAttack, a novel attack that exploits Beamforming Feedback Information (BFI) to reconstruct a user's Channel State Information (CSI), thereby compromising Wi-Fi physical-layer security.

The paper proposes ADAM, a novel and highly effective privacy attack that systematically extracts sensitive data from LLM agent memory by adaptively querying the victim agent's memory based on data distribution and entropy.

The paper introduces FORGE, a feedback-driven execution system that improves LLM-based binary analysis by interleaving reasoning and tool interaction, achieving high-quality vulnerability discovery on complex firmware binaries.

This paper systematically measures and explains how sequential model defenses can conflict, finding that 38.9% of ordered defense sequences cause measurable risk exacerbation due to anti-aligned parameter updates in shared layers.

This paper surveys model forensics in AI-native wireless networks, detailing key security problems and demonstrating practical workflows for verifying model authenticity and detecting malicious functions.

The paper proposes HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from task execution traces, leading to improved agent performance.

C-MIG is a novel retrieval-augmented generation framework that uses multi-view information gain to improve clinical diagnosis reasoning by providing richer, more nuanced reward signals than existing methods.

The paper proposes EAPO, an entropy-driven adaptive weighting method that dynamically adjusts the influence of positive samples during policy optimization to improve both response diversity and stability in open-ended QA.

The paper introduces a histogram-regularized latent diffusion model to synthesize highly realistic and subtype-specific pulmonary nodules in 3D CT volumes, addressing the limitations of existing methods that fail to capture accurate lesion-level intensity distributions.

The paper introduces AFUN, a model that predicts both the location (functional mask) and the motion (3D curve) for robot interaction, aiming to create a generalizable foundation model for understanding object functionality.

The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.