Yang Dai

This paper repurposes the statistical signals from data-poisoning backdoor attacks on contrastive learning (CL) models to create a multi-level, effective watermarking scheme for dataset intellectual property (IP) protection.

The paper introduces GraphIP-Bench, a unified benchmark that demonstrates that stealing Graph Neural Networks (GNNs) is relatively easy, and existing defenses often fail to maintain their integrity after the model is successfully extracted.

This paper systematically investigates how various plasticity interventions affect the vulnerability of deep reinforcement learning agents to backdoor attacks, finding that most interventions mitigate threats while one specific intervention exacerbates them.

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vision-Language-Action policies.

The paper introduces SkyShield, the first front-view monocular semantic occupancy benchmark for low-altitude urban UAV flight, along with a novel metric and model to address the unique safety challenges of aerial navigation.