MAPLE: manifold-aligned purification with logit-edge calibration for robust black-box adversarial defense

Summary

MAPLE is a black-box adversarial defense framework that pairs a fully convolutional Semantic Purification Network (SPN) with a Margin Calibration Classifier (MCC) initialized from the target classifier. The two components are trained through cyclic co-calibration to remove adversarial perturbations while enlarging the local classification margin. The paper reports that MAPLE consistently outperforms previous mainstream methods under diverse black-box attacks on CIFAR-10 and Mini-ImageNet.

Related items

• InfoAIRRI: Towards a Human-Readable, Machine-Resistant Reading InterfaceSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoSame Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety ClassifiersSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoCircuitBreak: Pruning a Sparse Safety Circuit of NeuronsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoRobust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological ImagingSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoQCLR: A Plug-in Robustification Module via Quantization for Contrastive Learning in Self-Supervised Skeleton-Based Human Action RecognitionSimilar attack · Arxiv (cs.RO + cs.CV security)