AINeutralarXiv – CS AI · 9h ago6/10
🧠
Exposing and Mitigating Temporal Attack in Deepfake Video Detection
Researchers reveal that spatiotemporal deepfake detection models are vulnerable to evasion attacks because they rely on fragile temporal spectrum cues rather than robust semantic understanding. The team proposes SpInShield, a defense framework using learnable spectral adversaries and shortcut suppression to improve detection robustness, achieving 21.30 percentage points better AUC against amplitude spectral attacks.