Wenqi Wei

QC-Bench: What Do Language Models Know About Quantum Computing?

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents

An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs

Adverseness vs. Equilibrium: Exploring Graph Adversarial Resilience through Dynamic Equilibrium

Protecting Membership Privacy through Adaptive Logit Scaling

DAG-Jailbreak: Enhancing Black-box Jailbreak Attacks and Defenses through DAG Dependency Analysis

SONAR: A Synthetic AI-Audio Detection Framework and Benchmark