USAD: Uncertainty-aware Statistical Adversarial Detection

• URL: http://arxiv.org/abs/2606.27832v1
• Date: Fri, 26 Jun 2026 08:19:00 GMT
• Title: USAD: Uncertainty-aware Statistical Adversarial Detection
• Abstract summary: Statistical adversarial detection (SAD) treats detection as a two-sample test.<n>We propose Uncertainty-aware Statistical Adversarial Detection (USAD), which explicitly captures uncertainty patterns.<n>USAD achieves superior detection performances over baseline methods against various adversarial attacks.
• Score: 17.557505716461034
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Statistical adversarial detection (SAD) treats detection as a two-sample test. Given a reference set of clean examples (CEs) and a batch of queries, potentially containing an unknown mixture of CEs and adversarial examples (AEs), SAD decides whether the query distribution drifts away from the CE distribution while controlling the false-alarm rate. Existing SAD-based methods mainly use maximum mean discrepancy (MMD) to measure the distributional discrepancy. However, MMD's distributional properties limit its ability to capture characteristic uncertainty patterns of AEs that are crucial for detection: AEs typically exhibit abnormal feature spread (i.e., global uncertainty) and instability under perturbations (i.e., local uncertainty). To close the gap, we propose Uncertainty-aware Statistical Adversarial Detection (USAD), which explicitly captures these uncertainty patterns with two new statistics: (1) Variance Discrepancy (VD), which measures the difference in feature spread between AEs and CEs to capture global uncertainty differences. (2) Perturbation-based Covariance Discrepancy (PCD), which compares feature covariance under Gaussian perturbations to capture local uncertainty differences. By aggregating VD and PCD, USAD achieves superior detection performances over baseline methods against various adversarial attacks, highlighting the importance of considering characteristic behaviors of AEs for effective SAD. Our code is available at: https://anonymous.4open.science/r/USAD.

Related papers

• Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction [8.306260695214972]
  We introduce Trustworthy Expert Split-conformal with Scaled Estimation for Efficient Reliable Adaptive intervals (TESSERA)<n>TESSERA provides per-sample uncertainty with reliable coverage guarantee, informative and adaptive prediction interval widths that track the absolute error.<n>We evaluate on protein-ligand binding affinity prediction under both independent and identically distributed (i.i.d.) and scaffold-based out-of-distribution (OOD) splits.
  arXiv  Detail & Related papers  (2025-10-17T01:51:33Z)
• Multidimensional Uncertainty Quantification via Optimal Transport [87.97146725546502]
  We take a multidimensional view on uncertainty quantification (UQ) by stacking complementary UQ measures into a vector.<n>VecUQ-OT shows high efficiency even when individual measures fail.
  arXiv  Detail & Related papers  (2025-09-26T14:09:03Z)
• Dealing with Uncertainty in Contextual Anomaly Detection [14.492457340456737]
  Contextual anomaly detection (CAD) aims to identify anomalies in a target (behavioral) variable conditioned on a set of contextual variables.<n>We propose a novel framework for CAD, normalcy score (NS), that explicitly models both the aleatoric and epistemic uncertainties.<n>We demonstrate that NS outperforms state-of-the-art CAD methods in both detection accuracy and interpretability.
  arXiv  Detail & Related papers  (2025-07-06T18:02:11Z)
• SConU: Selective Conformal Uncertainty in Large Language Models [59.25881667640868]
  We propose a novel approach termed Selective Conformal Uncertainty (SConU)<n>We develop two conformal p-values that are instrumental in determining whether a given sample deviates from the uncertainty distribution of the calibration set at a specific manageable risk level.<n>Our approach not only facilitates rigorous management of miscoverage rates across both single-domain and interdisciplinary contexts, but also enhances the efficiency of predictions.
  arXiv  Detail & Related papers  (2025-04-19T03:01:45Z)
• One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy [30.502354813427523]
  Statistical adversarial data detection (SADD) detects whether an upcoming batch contains adversarial examples (AEs)<n>We propose a two-pronged adversarial defense method, named Distributional-discrepancy-based Adversarial Defense (DAD)
  arXiv  Detail & Related papers  (2025-03-04T01:16:21Z)
• Revisiting Deep Ensemble Uncertainty for Enhanced Medical Anomaly Detection [34.14012444375776]
  We propose a Dual-space Uncertainty Estimation framework for medical anomaly detection. To balance agreement and disagreement for anomaly detection, we propose Redundancy-Aware Repulsion (RAR) We also develop Dual-Space Uncertainty (DSU) which utilizes the ensemble's uncertainty in input and output spaces.
  arXiv  Detail & Related papers  (2024-09-26T02:47:41Z)
• Beyond Perceptual Distances: Rethinking Disparity Assessment for Out-of-Distribution Detection with Diffusion Models [28.96695036746856]
  Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection. DM-based methods bring fresh insights to the field, yet remain under-explored. Our work has demonstrated state-of-the-art detection performances among DM-based methods in extensive experiments.
  arXiv  Detail & Related papers  (2024-09-16T08:50:47Z)
• Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score [62.54911162109439]
  Adversarial detection aims to determine whether a given sample is an adversarial one based on the discrepancy between natural and adversarial distributions. We propose a new statistic called expected perturbation score (EPS), which is essentially the expected score of a sample after various perturbations. We develop EPS-based maximum mean discrepancy (MMD) as a metric to measure the discrepancy between the test sample and natural samples.
  arXiv  Detail & Related papers  (2023-05-25T13:14:58Z)
• Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection [78.24964622317634]
  In this work, the formulation of Bayesian autoencoders (BAEs) is adopted to quantify the total anomaly uncertainty. To evaluate the quality of uncertainty, we consider the task of classifying anomalies with the additional option of rejecting predictions of high uncertainty. Our experiments demonstrate the effectiveness of the BAE and total anomaly uncertainty on a set of benchmark datasets and two real datasets for manufacturing.
  arXiv  Detail & Related papers  (2022-02-25T12:20:04Z)
• The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
  arXiv  Detail & Related papers  (2020-12-05T17:30:35Z)
• Localization Uncertainty Estimation for Anchor-Free Object Detection [48.931731695431374]
  There are several limitations of the existing uncertainty estimation methods for anchor-based object detection. We propose a new localization uncertainty estimation method called UAD for anchor-free object detection. Our method captures the uncertainty in four directions of box offsets that are homogeneous, so that it can tell which direction is uncertain.
  arXiv  Detail & Related papers  (2020-06-28T13:49:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.