Baoyuan Wu

So-Fake: Benchmarking Social Media Image Forgery Detection

Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization

Test-Time Poisoned Sample Detection by Exploiting Shallow Malicious Matching in Backdoored CLIP

AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models

Towards Explainable Bilingual Multimodal Misinformation Detection and Localization

DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection

$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection

Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection

ESpeW: Robust Copyright Protection for LLM-based EaaS via Embedding-Specific Watermark