Hui Wang

The paper proposes a tamper-proof fraud detection system that uses blockchain smart contracts to immutably record ML predictions and workflow executions, addressing the vulnerability of controllable audit trails.

This paper introduces TC-UMIA, a novel tri-class membership inference attack, demonstrating that machine unlearning can leak privacy risks to the retained data set, and evaluates defense mechanisms to mitigate this risk.

The paper introduces MAGE, a novel defensive framework that uses a dedicated 'shadow memory' to proactively detect and mitigate long-horizon threats against LLM agents during complex, multi-step interactions.

The paper introduces MoCo-EA, an evolutionary attack method that replaces standard crossover with a continuous Bézier curve interpolation to efficiently exploit the connected manifold structure of adversarial examples.

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reality gap' and perform poorly when simulating real-world cardiac interpretation workflows.

The paper introduces Moment-Video, a new benchmark that diagnoses the ability of video MLLMs to understand brief, critical visual events, revealing that current models struggle significantly with temporal fidelity.

The paper proposes the Shortcut Subspace Suppression (S^3) framework to improve deepfake detection generalization by explicitly identifying and suppressing method-specific shortcuts in learned feature representations.

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.