穩健且校準的多媒體真實內容檢測

摘要

生成式模型能合成高度逼真的內容（即所謂的深度偽造內容），這類技術已被大規模濫用，破壞數位媒體的真實性。現有的深度偽造檢測方法不可靠的原因有二：其一，事後區分非真實內容往往不可行（例如對已記憶樣本的檢測），導致假陽性率無上限；其二，檢測缺乏穩健性，對手僅需極少計算資源即可針對已知檢測器實現近乎完美的規避準確度。為解決這些局限，我們提出一種重合成框架，用於判定樣本是否真實，或是否可合理否認其真實性。我們針對高效能（即計算受限）對手，聚焦高精確度、低召回率的設定，做出兩項關鍵貢獻：首先，我們證明校準後的重合成方法在維持可控低假陽性率的同時，是驗證真實樣本最可靠的方法；其次，我們展示在相同計算預算下，現有方法易被規避，而我們的方法能實現對高效能對手的對抗穩健性。本方法支援多模態應用，並運用最先進的反轉技術。

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.

穩健且校準的多媒體真實內容檢測

Robust and Calibrated Detection of Authentic Multimedia Content

摘要

Support