15 papers
What Survives Self-Evolution: Provenance Marks in Copied Agent Harnesses
Jieyu Li, Jingya Li, Sheng Li +2
Agent harnesses, the prompt and tool code around a base model, leak. Claude Code's 512,000 lines were mirrored within hours of a packaging error. A plagiarist can pass a leaked har…
When Scene Text Hijacks the Scene: Uncovering, Exploiting, and Mitigating Rendered-Text Semantic Leakage in Image Generation Models
Feifei Li, Runjie Wang, Xiaohan Zhang +3
The reliability and accountability of image generative models (IGMs) are essential for building responsible and trustworthy AI systems. Recent IGMs, such as Nano Banana and GPT-Ima…
Fingerprinting Text-to-Image Diffusion Models via Collapsed Generation
Yuanmin Huang, Chen Chen, Geng Hong +5
Proprietary text-to-image diffusion models are increasingly distributed as hosted services and downloadable checkpoints, making their intellectual property (IP) protection an incre…
OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation
Zhenzhen Ren, Jiyan He, Xinpeng Zhang +5
Complex tasks often decompose into parallelizable yet interdependent subtasks, making orchestration critical to the performance of multi-agent systems (MAS). Existing evaluations t…
Only Train Once: Uncertainty-Aware One-Class Learning for Face Authenticity Detection
Qingchao Jiang, Zhenxuan Hou, Zhiying Zhu +3
The rapid evolution of generative paradigms has enabled the creation of highly realistic imagery, which escalates the risks of identity fraud and the dissemination of disinformatio…
Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning
Qingchao Jiang, Zhenxuan Hou, Zhiying Zhu +3
With the rapid development of deep generative models, forged facial images are massively exploited for illegal activities. Although existing synthetic face detection methods have a…
GTM: Simulating the World of Tools for AI Agents
Zhenzhen Ren, Xinpeng Zhang, Zhenxing Qian +4
The integration of external tools is pivotal for empowering Large Language Model (LLM) agents with real-world capabilities. However, training these agents through direct, continuou…
Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective
Nan Zhong, Mian Zou, Yiran Xu +4
The proliferation of AI-generated imagery poses escalating challenges for multimedia forensics, yet many existing detectors depend on assumptions about the internals of specific ge…
SimuFreeMark: A Noise-Simulation-Free Robust Watermarking Against Image Editing
Yichao Tang, Mingyang Li, Di Miao +3
The advancement of artificial intelligence generated content (AIGC) has created a pressing need for robust image watermarking that can withstand both conventional signal processing…
SyncGuard: Robust Audio Watermarking Capable of Countering Desynchronization Attacks
Zhenliang Gan, Xiaoxiao Hu, Sheng Li +2
Audio watermarking has been widely applied in copyright protection and source tracing. However, due to the inherent characteristics of audio signals, watermark localization and res…
MoFRR: Mixture of Diffusion Models for Face Retouching Restoration
Jiaxin Liu, Qichao Ying, Zhenxing Qian +4
The widespread use of face retouching on social media platforms raises concerns about the authenticity of face images. While existing methods focus on detecting face retouching, ho…
RoE-FND: A Case-Based Reasoning Approach with Dual Verification for Fake News Detection via LLMs
Yuzhou Yang, Yangming Zhou, Zhiying Zhu +3
The proliferation of deceptive content online necessitates robust Fake News Detection (FND) systems. While evidence-based approaches leverage external knowledge to verify claims, e…
CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Models
Zhenzhen Ren, GuoBiao Li, Sheng Li +2
Despite providing superior performance, open-source large language models (LLMs) are vulnerable to abusive usage. To address this issue, recent works propose LLM fingerprinting met…
Adversarial Shallow Watermarking
Guobiao Li, Lei Tan, Yuliang Xue +4
Recent advances in digital watermarking make use of deep neural networks for message embedding and extraction. They typically follow the ``encoder-noise layer-decoder''-based archi…
What Makes Good Few-shot Examples for Vision-Language Models?
Zhaojun Guo, Jinghui Lu, Xuejing Liu +3
Despite the notable advancements achieved by leveraging pre-trained vision-language (VL) models through few-shot tuning for downstream tasks, our detailed empirical study highlight…