研究
推動AI 信任科學的發展
我們的研究聚焦於深度偽造偵測、合成媒體鑑識以及對抗強健性。我們公開發表研究成果，以推動此領域的進展，並協助客戶始終領先於新興威脅。
13
研究論文
5
研究領域
7
開放資料集
3
即將推出
出版品與報告
來自 Scam AI 團隊的研究，涵蓋深度偽造偵測、文件偽造、年齡推估等多個方向。
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
在 arXiv 上檢視 - 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
在 arXiv 上檢視 - 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
在 arXiv 上檢視 - 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
在 Scholar 上檢視
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
在 arXiv 上檢視 - 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
在 arXiv 上檢視
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
在 arXiv 上檢視 - 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
在 arXiv 上檢視
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
在 Scholar 上檢視 - 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
在 Scholar 上檢視
Interview Tech
資料集
精選資料集，協助研究人員對偵測模型進行基準測試。每個資料集皆有獨立頁面，包含引用資訊、論文連結以及須經電子郵件驗證的下載入口。
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.