8 papers
Open-Jev Judgments on CallScreenBench: Calibrated One-Pass Scam Screening with a Small Language Model
Simiao Ren, Kidus Zewde, Xingyu Shen +6
Screening a phone call for fraud needs a trustworthy probability after every caller turn, in milliseconds. Jev-style typed decisions promise exactly that: declared options go in, o…
Agents That Edit Documents: Measuring Agentic PDF Forgery Against a Non-Agentic Control
Simiao Ren, Ankit Raj, Tommy Duong +6
AI agents that carry a multi-step computer task through on their own became ordinary tools in the past year, and the same autonomy is available to anyone whose task is harmful. We…
ChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector Evaluation
Dennis Ng, Xingyu Shen, Ankit Raj +6
An image tool can change its underlying generator while retaining its public name, making version attribution from online posts ambiguous. We study this problem after the ChatGPT I…
A Corpus of Real Scam- and Spam-Call Conversations from an Active Voice-Agent Honeypot
Ethan Traister, Dennis Tsang Ng, Siyu Zhang +7
Real conversations between fraudsters and their targets are among the most informative artifacts for studying telephone scams, yet also the scarcest: passive honeypots overwhelming…
When the Forger Is the Judge: GPT-Image-2 Cannot Recognize Its Own Faked Documents
Jiaqi Wu, Yuchen Zhou, Dennis Tsang Ng +5
OpenAI's GPT-Image-2 has effectively erased the visual boundary between authentic and AI-edited document images: a single number on a receipt can be replaced in under a second for…
A Synthetic Eye Movement Dataset for Script Reading Detection: Real Trajectory Replay on a 3D Simulator
Kidus Zewde, Yuchen Zhou, Dennis Ng +6
Large vision-language models have achieved remarkable capabilities by training on massive internet-scale data, yet a fundamental asymmetry persists: while LLMs can leverage self-su…
Chinese Language Is Not More Efficient Than English in Vibe Coding: A Preliminary Study on Token Cost and Problem-Solving Rate
Simiao Ren, Xingyu Shen, Yuchen Zhou +3
A claim has been circulating on social media and practitioner forums that Chinese prompts are more token-efficient than English for LLM coding tasks, potentially reducing costs by…
GPT4o-Receipt: A Dataset and Human Study for AI-Generated Document Forensics
Yan Zhang, Simiao Ren, Ankit Raj +6
Can humans detect AI-generated financial documents better than machines? We present GPT4o-Receipt, a benchmark of 1,235 receipt images pairing GPT-4o-generated receipts with authen…