RA-Det:通过鲁棒性不对称性实现对AI生成图像的通用检测
RA-Det: Towards Universal Detection of AI-Generated Images via Robustness Asymmetry
AI总结:
RA-Det通过鲁棒性不对称性检测AI生成图像,实现通用且高效的检测方法。
摘要:
最近的图像生成器产生出逼真的内容,这削弱了下游识别系统的可靠性。随着视觉外观线索变得不明显,依赖于刑侦线索或高层表示的外观驱动检测器失去稳定性。这促使从外观转向行为,关注图像如何响应受控扰动,而不是它们看起来如何。在本工作中,我们识别出一个简单且通用的行为信号。自然图像在小的、结构化的扰动下保持稳定的语义表示,而生成图像则表现出明显更大的特征漂移。我们将这种现象称为鲁棒性不对称性,并提供理论分析,建立这一不对称性与生成模型记忆倾向之间的下界,解释其在不同架构中的普遍性。基于这一见解,我们引入了鲁棒性不对称性检测(RA-Det),一种行为驱动的检测框架,将鲁棒性不对称性转化为可靠的决策信号。在14种不同的生成模型和超过10种强大的检测器上进行评估,RA-Det实现了优越的性能,平均性能提高了7.81个百分点。该方法数据和模型无关,不需要生成器指纹,并能跨未见过的生成器进行迁移。这些结果表明,鲁棒性不对称性是一种稳定的、通用的合成图像检测线索,并且精心设计的探测可以将这一线索转化为实用的、通用的检测器。源代码在GitHub上公开。
英文摘要:
Recent image generators produce photo-realistic content that undermines the reliability of downstream recognition systems. As visual appearance cues become less pronounced, appearance-driven detectors that rely on forensic cues or high-level representations lose stability. This motivates a shift from appearance to behavior, focusing on how images respond to controlled perturbations rather than how they look. In this work, we identify a simple and universal behavioral signal. Natural images preserve stable semantic representations under small, structured perturbations, whereas generated images exhibit markedly larger feature drift. We refer to this phenomenon as robustness asymmetry and provide a theoretical analysis that establishes a lower bound connecting this asymmetry to memorization tendencies in generative models, explaining its prevalence across architectures. Building on this insight, we introduce Robustness Asymmetry Detection (RA-Det), a behavior-driven detection framework that converts robustness asymmetry into a reliable decision signal. Evaluated across 14 diverse generative models and against more than 10 strong detectors, RA-Det achieves superior performance, improving the average performance by 7.81 percent. The method is data- and model-agnostic, requires no generator fingerprints, and transfers across unseen generators. Together, these results indicate that robustness asymmetry is a stable, general cue for synthetic-image detection and that carefully designed probing can turn this cue into a practical, universal detector. The source code is publicly available at Github.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。