Adversarial Training in Low-Label Regimes With Margin-Based Interpolation

Summary

Researchers propose margin-based interpolation, a semisupervised adversarial training method for low-label regimes that adapts perturbation strength to each data point's vulnerability and the distribution of pseudolabels. It interpolates between clean and adversarial data and adds global epsilon scheduling that gradually raises the perturbation bound. On CIFAR-10, SVHN, CIFAR-100 and STL-10, the method improves natural accuracy and robustness against PGD and AutoAttack compared to baselines.

Related items

• LowA Valid Watermark Is Not a Valid Identity: Spatial-Spectral Adversarial Face Evasion with Watermark PreservationSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoTopology-aware dynamic co-evolution for robust graph learningSimilar attack · OpenAlex (peer-reviewed AI security)
• InfoDecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and VisionSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoAIRRI: Towards a Human-Readable, Machine-Resistant Reading InterfaceSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoLimits of Statistical Assurance for Embodied and Agentic AI under Adaptive AdversariesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)