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
33 results for “keyword:"certified robustness"” in ICLR 2027. 7 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Freeze the Weights, Not the Graph: Prompt-Retrievable Watermarks for Frozen Diffusion Models with Certified Retrieval▼1351.33
[PDF]Enabling Certified Robustness for LLMs at Large Perturbation Radii via Corruption-Rate Randomization▼1.1k3.25
[PDF]Does Certified Robustness Generalize? A Neural Network Verification Study of Distribution Shift▼1601.50
[PDF]TaylorSSM: Dependence-Preserving Robustness Certification for Selective State-Space Models▲3.0k2.33
[PDF]Improved Certified Robustness and Adversarial Attacks for Rate-Encoded Spiking Neural Networks▲5.4k3.00
[PDF]STOCHASTIC ODE-GUARD: ANTI-CONCENTRATION BOUNDS FOR NEURAL SDE CLASSIFIERS WITH APPLICATION TO ADVERSARIALLY ROBUST INTRUSION DETECTION▼1351.33
[PDF]GTCert: Certified Robustness for Graph Transformers via Attention-Mask Randomized Smoothing▼1351.33
Withdrawn or desk rejected (7)
[PDF]SpecCert: Deterministic Joint Certification and Margin-Explicit Training for Graph Neural NetworksWithdrawn2.00
[PDF]Correcting Errors, Correctly: Certified Robustness for Error-Correcting Output CodesWithdrawn1.33