稳健且可校准的真实多媒体内容检测

摘要

生成模型能够合成高度逼真的内容，即所谓的深度伪造内容，这些技术已被大规模滥用以破坏数字媒体的真实性。现有深度伪造检测方法不可靠的原因有二：其一，事后鉴别非真实内容往往不可行（例如面对记忆样本），导致假阳性率（FPR）无界上升；其二，检测缺乏鲁棒性，攻击者仅需极少计算资源即可针对已知检测器实现近乎完美的规避。为应对这些局限，我们提出一种重合成框架来判断样本是否真实，或其真实性是否可被合理质疑。针对计算受限的高效攻击者场景，我们聚焦高精度、低召回率的设定做出两项关键贡献：首先，我们证明经过校准的重合成方法是在保持可控低假阳性率的同时验证真实样本的最可靠途径；其次，我们表明该方法能实现对高效攻击者的对抗鲁棒性，而现有方法在相同计算预算下极易被规避。我们的方案支持多模态数据，并利用了最先进的逆向映射技术。

English

Generative models can synthesize highly realistic content, so-called deepfakes, that are already being misused at scale to undermine digital media authenticity. Current deepfake detection methods are unreliable for two reasons: (i) distinguishing inauthentic content post-hoc is often impossible (e.g., with memorized samples), leading to an unbounded false positive rate (FPR); and (ii) detection lacks robustness, as adversaries can adapt to known detectors with near-perfect accuracy using minimal computational resources. To address these limitations, we propose a resynthesis framework to determine if a sample is authentic or if its authenticity can be plausibly denied. We make two key contributions focusing on the high-precision, low-recall setting against efficient (i.e., compute-restricted) adversaries. First, we demonstrate that our calibrated resynthesis method is the most reliable approach for verifying authentic samples while maintaining controllable, low FPRs. Second, we show that our method achieves adversarial robustness against efficient adversaries, whereas prior methods are easily evaded under identical compute budgets. Our approach supports multiple modalities and leverages state-of-the-art inversion techniques.

稳健且可校准的真实多媒体内容检测

Robust and Calibrated Detection of Authentic Multimedia Content

摘要

Support