Nguyen Hung-Quang

Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks

Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models

Unveiling Concept Attribution in Diffusion Models

Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks

Fooling the Textual Fooler via Randomizing Latent Representations