CogniDir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection
CogniDir is introduced, an adaptive distributional learning framework that reformulates robust detection as a dynamic data mixture optimization problem for social media content safety by formalizing mechanism-specific cognitive adversarial paradigms to systematically expose deep-seated detector vulnerabilities.
Zhao Tong, Chun-Lin Gong, Yimeng Gu et al.
· 3 citations