Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning

ICLROral2026

Authors: Hao Tan, jun lan, Zichang Tan, Senyuan Shi, Ajian Liu, Chuanbiao Song, Huijia Zhu, Weiqiang Wang, Jun Wan, Zhen Lei
Affiliation: Institute of automation, Chinese Academy of Sciences
Venue: ICLR 2026
Track: Oral

TL;DR

We introduce a MLLM-based detector for transparent deepfake detection, along with a holistic dataset for deepfake detection.

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

reasoning dataset llm

← All ICLR 2026 Oral papers · Browse the whole archive