11 papers
ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection
Xiaojing Chen, Xinyu Lu, Changtao Miao +1
AI-generated videos are becoming increasingly realistic, raising serious concerns about misinformation, content authenticity, and media trust. Reliable AI-generated video detection…
SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
Hao Cheng, Changtao Miao, Tianle Song +21
Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabilities enable complex real-world…
TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images
Yuning Zhang, Changtao Miao, Mingyu Liao +5
Recent AI-generated image (AIGI) detectors perform well on natural-image benchmarks, but their behavior on text-rich forgeries, such as fabricated screenshots, documents, and news…
GIFGuard: Proactive Forensics against Deepfakes in Facial GIFs via Spatiotemporal Watermarking
Shupeng Che, Zhiqing Guo, Changtao Miao +2
The rapid evolution of deepfake technology poses an unprecedented threat to the authenticity of Graphics Interchange Format (GIF) imagery, which serves as a representative of short…
LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
Jing Huang, Zhiya Tan, Shutao Gong +6
As large vision language models (VLMs) advance, their capabilities in multilingual visual question answering (mVQA) have significantly improved. Chain-of-thought (CoT) reasoning ha…
DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning
Fanwei Zeng, Changtao Miao, Jing Huang +9
The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety. Existing forensic methods mainly re…