NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
54 results for “keyword:"deepfake detection"” in ICLR 2027. 25 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What a Deepfake Score Does Not Tell You: Same-Source Controls for Face-Forgery and Generated-Video Detectors▲3.0k2.33
Withdrawn or desk rejected (25)
[PDF]Periodic Gradient-Variance Suppression on SVD-Adapted Residuals for Cross-Generator Deepfake DetectionWithdrawn1.75
[PDF]HyperDetect: Hierarchy-Aware Representation Learning for Generalizable Deepfake DetectionDesk rejected2.00
[PDF]MoCouple: Learning Fine-Grained Motion Coupling for Generalizable Talking-Face Forgery DetectionWithdrawn1.67
[PDF]Not All Channels Are Equal: Perturbation-Invariant Channel Selection for Robust AI-Generated Image DetectionWithdrawn2.00
[PDF]AOI: All-in-One Audio Deepfake Detection via Evidence-Grounded Rationales and On-Policy DistillationDesk rejected2.00
[PDF]Faithful Is Not Forensic: Robust Intervention-based Forensic Testing (RIFT) for Auditing Deepfake DetectorsWithdrawn1.67