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
15 results for “keyword:"adversarial examples"” in ICLR 2027. 5 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]MissClick: Execution-Aware Adversarial Attacks on Coordinate Generation in GUI Grounding Models▲3.0k2.33
[PDF]LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse▲153.33
[PDF]Interpretable Adversarial Defense via Class-Aware Neuron Sensitivity Attribution and Recalibration▼1.2k1.67
[PDF]SAR-DiSCO: Differentiable Scattering Coefficient Optimization for 3D Adversarial Attacks on SAR Target Recognition▼11k2.33
[PDF]Adversarial Scenario Attack: Query-Efficient Black-Box Generation of Natural Adversarial Examples▼4.3k2.00
[PDF]AMEND: Attention Misalignment for Natural Adversarial Attacks against Object Detectors▼1.2k1.67
[PDF]Morpheus: Modality-Agnostic Adversarial Attack from Leaked Models in Federated Learning▲5.4k3.00
[PDF]Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures▼4.5k2.67
Withdrawn or desk rejected (5)
[PDF]Improving Randomized Smoothing Certificates Through Guiding Diffusion-based DenoisersDesk rejected
[PDF]Silent Loss of Image Conditioning Under Direct Fooling Objectives: A Diagnostic for Amortized Adversarial AttacksWithdrawn1.67