Pesquisa
Avançando a ciência da confiança em IA
Nossa pesquisa se concentra em detecção de deepfakes, perícia forense de mídia sintética e robustez contra ataques adversariais. Publicamos nossas descobertas para impulsionar a área e manter nossos clientes à frente das ameaças emergentes.
13
Artigos de pesquisa
5
Áreas de pesquisa
7
Conjuntos de dados abertos
3
Em breve
Publicações e relatórios
Pesquisa da equipe da Scam AI sobre detecção de deepfakes, falsificação de documentos, estimativa de idade e muito mais.
Document Forgery
- DOCFORGE-BENCH: A Comprehensive Benchmark for Document Forgery Detection and Analysis
Zengqi Zhao, Weidi Xia, Peter Wei, Yan Zhang, Yiyi Zhang, Jane Mo, Tiannan Zhang, Yuanqin Dai, Zexi Chen, Simiao Ren
Ver em arXiv - When the Forger Is the Judge: GPT-Image-2 Cannot Recognize Its Own Faked Documents
Jiaqi Wu, Yuchen Zhou, Dennis Tsang Ng, Xingyu Shen, Kidus Zewde, Ankit Raj, Tommy Duong, Simiao Ren
Ver em arXiv - AIForge-Doc: A Benchmark for Detecting AI-Forged Tampering in Financial and Form Documents
Jiaqi Wu, Yuchen Zhou, Muduo Xu, Zisheng Liang, Simiao Ren, Jiayu Xue, Meige Yang, Siying Chen, Jingheng Huan
Ver em arXiv - Can Multi-modal (reasoning) LLMs detect document manipulation?
Zisheng Liang, Kidus Zewde, Rudra Pratap Singh, Disha Patil, Zexi Chen, Jiayu Xue, Yao Yao, Yifei Chen, Qinzhe Liu, Simiao Ren
Ver em Scholar
Age Estimation
- Can a Teenager Fool an AI? Evaluating Low-Cost Cosmetic Attacks on Age Estimation Systems
Xingyu Shen, Tommy Duong, Xiaodong An, Zengqi Zhao, Zebang Hu, Haoyu Hu, Ziyou Wang, Finn Guo, Simiao Ren
Ver em 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, Ankit Raj, Albert Dai, Caroline Zhang, Yuan Xu, Zexi Chen, Siqi Wu, Chen Gong, Yuxin Zhang
Ver em 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, Xingyu Shen, Jenny Wu, Yuchen Zhou, Tommy Duong, Zikang Zhang, Ethan Traister
Ver em arXiv - How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study
Simiao Ren, Yuchen Zhou, Xingyu Shen, Kidus Zewde, Tommy Duong, George Huang, Neo Tiangratanakul, Dennis Ng, En Wei, Jiayu Xue
Ver em arXiv
Deepfake Detection
- Do deepfake detectors work in reality?
Simiao Ren, Disha Patil, Kidus Zewde, Dennis Ng, Hengwei Xu, Shengkai Jiang, Ramini Desai, Ning-Yau Cheng, Yining Zhou, Ragavi Muthukrishnan
Ver em Scholar - Can Multi-modal (reasoning) LLMs work as deepfake detectors?
Simiao Ren, Yao Yao, Kidus Zewde, Zisheng Liang, Ning-Yau Cheng, Xiaoou Zhan, Qinzhe Liu, Yifei Chen, Hengwei Xu
Ver em Scholar
Interview Tech
Conjuntos de dados
Conjuntos de dados selecionados para ajudar pesquisadores a avaliar modelos de detecção. Cada conjunto de dados tem sua própria página com a citação, o link do artigo e um download protegido por e-mail.
A real-world faceswap collection used to evaluate deepfake detectors against in-the-wild manipulations rather than lab-only synthetics.
Financial and form documents tampered by a suite of AI editing tools, paired with originals — used to benchmark document forgery detectors.
A v2 expansion of AIForge-Doc covering GPT-Image-2 generated tampering — used in the 'When the Forger Is the Judge' benchmark.
Self-reported AI-generated images collected from Twitter during the first week of GPT-Image-2 deployment — captures real-world distribution shift.
Faces with low-cost cosmetic adversarial perturbations designed to defeat age estimation systems — used in 'Can a Teenager Fool an AI?'.
Fully synthetic receipts generated by GPT-4o, paired with a human-study evaluation of detectability — used for AI-generated document forensics research.
Synthetic eye-movement trajectories rendered through a 3D eye simulator, replaying real reading paths — used for script reading detection research.
Tem interesse em colaborar?
Atuamos em parceria com instituições acadêmicas e laboratórios do setor em pesquisas sobre detecção de deepfakes.
Entre em contato