activity
20242026
collaborators

10 papers

cs.CR2026

When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive Learning

Yiming Chen, Kemou Li, Haiwei Wu +1

Backdoor attacks in multimodal contrastive learning (MCL) have garnered growing attention in recent years, as many downstream tasks critically depend on pre-trained MCL models. Exi…

cs.CV2026

SEED: Simple ViT and Evolving Harness for Explainable Text Forgery Detection

Kahim Wong, Kemou Li, Yiming Chen +2

AI-assisted image editing threatens trust in financial, legal, and identity records. The GenText-Forensics Challenge at ACM MM 2026 addresses this by requiring structured forensic…

cs.CV2026

NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild

Aleksandr Gushchin, Khaled Abud, Ekaterina Shumitskaya +51

This paper presents an overview of the NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild, held in conjunction with the NTIRE workshop at CVPR 2026. The goal o…

cs.CL2026

NNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection

Kahim Wong, Kemou Li, Haiwei Wu +1

LLM-generated text (LGT) detection is essential for reliable forensic analysis and for mitigating LLM misuse. Existing LGT detectors can generally be categorized into two broad cla…

cs.CV2026

FeatDistill: A Feature Distillation Enhanced Multi-Expert Ensemble Framework for Robust AI-generated Image Detection

Zhilin Tu, Kemou Li, Fengpeng Li +3

The rapid iteration and widespread dissemination of deepfake technology have posed severe challenges to information security, making robust and generalizable detection of AI-genera…

cs.CV2025

Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation

Yuhao He, Jinyu Tian, Haiwei Wu +1

The rapid advancement of diffusion models has enhanced their image inpainting and editing capabilities but also introduced significant societal risks. Adversaries can exploit user…