Research
Advancing the science of AI trust
We research deepfake detection, synthetic media forensics, and adversarial robustness — publishing our findings to advance the field and keep customers ahead of emerging threats.
13
Research papers
5
Research areas
7
Open datasets
3
Coming soon
Publications & reports
Document Forgery
DOCFORGE-BENCH: A Comprehensive Benchmark for Document Forgery Detection and Analysis
Zengqi Zhao, Weidi Xia, Peter Wei, et al.
arXiv →When the Forger Is the Judge: GPT-Image-2 Cannot Recognize Its Own Faked Documents
Jiaqi Wu, Yuchen Zhou, Dennis Tsang Ng, et al.
arXiv →AIForge-Doc: A Benchmark for Detecting AI-Forged Tampering in Financial and Form Documents
Jiaqi Wu, Yuchen Zhou, Muduo Xu, et al.
arXiv →Can Multi-modal (reasoning) LLMs detect document manipulation?
Zisheng Liang, Kidus Zewde, et al.
Google Scholar →Can fully synthetic AI-generated financial documents fool humans?
Coming soon
Age Estimation
Can a Teenager Fool an AI? Evaluating Low-Cost Cosmetic Attacks on Age Estimation Systems
Xingyu Shen, Tommy Duong, et al.
arXiv →Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures
Simiao Ren, Xingyu Shen, et al.
arXiv →
AI-Generated Detection
GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
Kidus Zewde, Simiao Ren, et al.
arXiv →How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study
Simiao Ren, Yuchen Zhou, et al.
arXiv →Survey on the development of AI-generated and deepfake detection
Coming soon
Deepfake Detection
Do deepfake detectors work in reality?
Simiao Ren, Disha Patil, Kidus Zewde, et al.
Google Scholar →Can Multi-modal (reasoning) LLMs work as deepfake detectors?
Simiao Ren, Yao Yao, Kidus Zewde, et al.
Google Scholar →
Interview Tech
Reading gaze estimation dataset for robust cheating identification
Coming soon
Open datasets
Real-World Faceswap Dataset (RWFS)
A real-world faceswap collection used to evaluate deepfake detectors against in-the-wild manipulations rather than lab-only synthetics.
Log in to downloadAI-edit document forgery dataset (AIForge-Doc)
Financial and form documents tampered by a suite of AI editing tools, paired with originals — used to benchmark document forgery detectors.
Log in to downloadAIForge-Doc v2.0 (GPT-Image-2 document forgeries)
A v2 expansion of AIForge-Doc covering GPT-Image-2 generated tampering — used in the 'When the Forger Is the Judge' benchmark.
Log in to downloadGPT-Image-2 Twitter Dataset
Self-reported AI-generated images collected from Twitter during the first week of GPT-Image-2 deployment — captures real-world distribution shift.
Log in to downloadAdversarial age estimation attack dataset
Faces with low-cost cosmetic adversarial perturbations designed to defeat age estimation systems — used in 'Can a Teenager Fool an AI?'.
Log in to downloadFully-synthetic AI-generated receipt (GPT-4o-receipt)
Fully synthetic receipts generated by GPT-4o, paired with a human-study evaluation of detectability — used for AI-generated document forensics research.
Log in to downloadSimulated gaze estimation for reading dataset
Synthetic eye-movement trajectories rendered through a 3D eye simulator, replaying real reading paths — used for script reading detection research.
Log in to downloadInterested in collaborating?
We partner with academic institutions and industry labs on deepfake detection research.