7 papers
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…
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…
Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models
Jianwei Fei, Yunshu Dai, Zhihua Xia +4
Model fingerprinting, embedding user-specific identifiers (fingerprints) into generated outputs, has recently emerged as a popular solution to protect the intellectual property rig…
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…
An End-to-End Model for Logits-Based Large Language Models Watermarking
Kahim Wong, Jicheng Zhou, Jiantao Zhou +1
The rise of LLMs has increased concerns over source tracing and copyright protection for AIGC, highlighting the need for advanced detection technologies. Passive detection methods…
Rethinking Image Forgery Detection via Soft Contrastive Learning and Unsupervised Clustering
Haiwei Wu, Yiming Chen, Jiantao Zhou +1
Image forgery detection aims to detect and locate forged regions in an image. Most existing forgery detection algorithms formulate classification problems to classify pixels into f…