FACT用动态工具组合检测AI生成图像，适应新模型更有效。
FACT: A Forensic Agent with Compiled Tool-Use Trajectories for AI-Generated Image Detection
- 根据图像自动生成检测工具调用序列，灵活选择分析手段。
- 在6个基准上优于现有方法，对未见过的生成器仍保持高精度。
- 适合需要持续更新检测能力的安防与内容审核场景。
AI生成图像检测面临开放世界挑战：新型生成器产出高度逼真的图像，使视觉痕迹更难识别。现有检测器通常依赖固定的一组取证线索，因此对某一类生成器有效的检测器可能在另一类上失效。我们提出FACT（Forensic Agent with Compiled Tool-use Trajectories），一种基于图像条件的取证工具使用策略学习框架。不同于固定检测流程，FACT自主决定调用哪些取证工具，解读返回证据，并在收集到足够证据时停止。其采用Evolve--Distill--Refine流水线：先演化出可执行验证的取证技能，将其编译为动作-观测工具使用轨迹，再提炼为紧凑代理，并通过成本感知的GRPO进行策略优化。在两个内部和四个公开基准上，FACT在所有对比方法中表现最佳，包括对近期未见生成器、深度伪造及篡改图像的检测任务。
原文摘要 · Abstract (English)
AI-generated image detection is increasingly open-world: new image generators produce highly realistic images that make visual artifacts harder to identify. Existing detectors usually rely on a fixed set of forensic cues, so a detector that works well for one generator family may fail on another. We introduce FACT (Forensic Agent with Compiled Tool-use Trajectories), which learns an image-conditioned tool-use policy for forensic analysis. Instead of applying a fixed detector, FACT decides which forensic tools to call, interprets the returned evidence, and stops when sufficient evidence has been collected. FACT follows an Evolve--Distill--Refine pipeline: it evolves an execution-verified forensic skill, compiles the skill into action--observation tool-use trajectories, distills them into a compact agent, and refines the policy with cost-aware GRPO. Across two internal and four public benchmarks, FACT achieves the best performance among all compared methods, including on recent unseen generators, deepfakes, and manipulated images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。