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
13 results for “keyword:"adversarial perturbations"” in ICLR 2027. 8 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Obscrowd: Joint Face-Localized Identity Protection for Multi-Portrait Images under Generative Editing▲3.8k2.50
[PDF]SPIN: Image Immunization Against Diffusion Editing via Single-Step Projection in Stochastic Neighborhoods▲14k3.00
[PDF]Fragile by Distillation: Native-Objective Vicinal Alignment for Reliable Synthetic Sets▼5.8k2.33
[PDF]Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision–Language Models▼4.5k2.67
[PDF]Distributed Geographic Identity Encoding in Vision-Language Models: From Linear Probing to Sparse Autoencoder Feature Ablation, and Why Post-Hoc Debiasing Fails▲11.00
[PDF]Inducing Hallucinations in Video Large Language Models by Exploiting Spatiotemporal Corruption Sensitivity▲3.0k2.33
Withdrawn or desk rejected (8)
[PDF]Silent Loss of Image Conditioning Under Direct Fooling Objectives: A Diagnostic for Amortized Adversarial AttacksWithdrawn1.67