# PurSAMERE: Reliable Adversarial Purification via Sharpness-Aware Minimization of Expected Reconstruction Error Source: [PurSAMERE: Reliable Adversarial Purification via Sharpness-Aware Minimization of Expected Reconstruction Error]() Collection index: [llms.txt]() Data updated: 2026-02-10T05:00:04.897Z Authors: Vinh Hoang, Sebastian Krumscheid, Holger Rauhut, Ra\\'ul Tempone Published: 2026-02-06T00:06:30.000Z ## Abstract We propose a novel deterministic purification method to improve adversarial robustness by mapping a potentially adversarial sample toward a nearby sample that lies close to a mode of the data distribution, where classifiers are more reliable. We design the method to be deterministic to ensure reliable test accuracy and to prevent the degradation of effective robustness observed in stochastic purification approaches when the adversary has full knowledge of the system and its randomness. We employ a score model trained by minimizing the expected reconstruction error of noise-corrupted data, thereby learning the structural characteristics of the input data distribution. Given a potentially adversarial input, the method searches within its local neighborhood for a purified sample that minimizes the expected reconstruction error under noise corruption and then feeds this purified sample to the classifier. During purification, sharpness-aware minimization is used to guide the purified samples toward flat regions of the expected reconstruction error landscape, thereby enhancing robustness. We further show that, as the noise level decreases, minimizing the expected reconstruction error biases the purified sample toward local maximizers of the Gaussian-smoothed density; under additional local assumptions on the score model, we prove recovery of a local maximizer in the small-noise limit. Experimental results demonstrate significant gains in adversarial robustness over state-of-the-art methods under strong deterministic white-box attacks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-10 (test) (Clean & BPDA20 Adversarial Accuracy)](): Image Classification; CIFAR-10 (test); Clean Accuracy: 91.18. - [Adversarial Robustness on CIFAR-10 (test)](): Adversarial Robustness; CIFAR-10 (test); Attack Success Rate (ASR): not recorded. ## Original sources and implementation [Original paper]() [PDF]()