Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples

• URL: http://arxiv.org/abs/2506.03765v1
• Date: Wed, 04 Jun 2025 09:29:11 GMT
• Title: Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples
• Authors: Sicong Han, Chenhao Lin, Zhengyu Zhao, Xiyuan Wang, Xinlei He, Qian Li, Cong Wang, Qian Wang, Chao Shen,
• Abstract summary: Prediction Inconsistency Detector (PID) is a lightweight and generalizable detection framework.<n>PID is compatible with both naturally and adversarially trained primal models.<n>It outperforms four detection methods across 3 white-box, 3 black-box, and 1 mixed adversarial attacks.
• Score: 31.535244194865236
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Adversarial detection protects models from adversarial attacks by refusing suspicious test samples. However, current detection methods often suffer from weak generalization: their effectiveness tends to degrade significantly when applied to adversarially trained models rather than naturally trained ones, and they generally struggle to achieve consistent effectiveness across both white-box and black-box attack settings. In this work, we observe that an auxiliary model, differing from the primary model in training strategy or model architecture, tends to assign low confidence to the primary model's predictions on adversarial examples (AEs), while preserving high confidence on normal examples (NEs). Based on this discovery, we propose Prediction Inconsistency Detector (PID), a lightweight and generalizable detection framework to distinguish AEs from NEs by capturing the prediction inconsistency between the primal and auxiliary models. PID is compatible with both naturally and adversarially trained primal models and outperforms four detection methods across 3 white-box, 3 black-box, and 1 mixed adversarial attacks. Specifically, PID achieves average AUC scores of 99.29\% and 99.30\% on CIFAR-10 when the primal model is naturally and adversarially trained, respectively, and 98.31% and 96.81% on ImageNet under the same conditions, outperforming existing SOTAs by 4.70%$\sim$25.46%.

Related papers

• Deep learning models are vulnerable, but adversarial examples are even more vulnerable [7.097468024050319]
  This study first empirically finds that image-based adversarial examples are notably sensitive to occlusion.<n>We propose Sliding Window Mask-based Adrial Example Detection (SWM-AED), which avoids catastrophic overfitting of conventional adversarial training.<n> Evaluations across classifiers and attacks on CIFAR-10 demonstrate robust performance, with accuracy over 62% in most cases and up to 96.5%.
  arXiv  Detail & Related papers  (2025-11-07T08:43:08Z)
• The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage [71.8564105095189]
  We introduce N-Gram Coverage Attack, a membership inference attack that relies solely on text outputs from the target model.<n>We first demonstrate on a diverse set of existing benchmarks that N-Gram Coverage Attack outperforms other black-box methods.<n>We find that more recent models, such as GPT-4o, exhibit increased robustness to membership inference.
  arXiv  Detail & Related papers  (2025-08-13T08:35:16Z)
• AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning [93.77763753231338]
  Adversarial Contrastive Prompt Tuning (ACPT) is proposed to fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries. We show that ACPT can detect 7 state-of-the-art query-based attacks with $>99%$ detection rate within 5 shots. We also show that ACPT is robust to 3 types of adaptive attacks.
  arXiv  Detail & Related papers  (2024-08-04T09:53:50Z)
• PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis [2.5347892611213614]
  Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. We develop a practical method for this characteristic of model prediction and feature attribution to detect adversarial samples. Our approach demonstrates competitive performance even when an adversary is aware of the defense mechanism.
  arXiv  Detail & Related papers  (2024-04-12T21:22:21Z)
• Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness [52.9493817508055]
  We propose Pre-trained Model Guided Adversarial Fine-Tuning (PMG-AFT) to enhance the model's zero-shot adversarial robustness. Our approach consistently improves clean accuracy by an average of 8.72%.
  arXiv  Detail & Related papers  (2024-01-09T04:33:03Z)
• Adversarial defense based on distribution transfer [22.14684430074648]
  The presence of adversarial examples poses a significant threat to deep learning models and their applications. Existing defense methods provide certain resilience against adversarial examples, but often suffer from decreased accuracy and generalization performance. This paper proposes a defense method based on distribution shift, leveraging the distribution transfer capability of a diffusion model for adversarial defense.
  arXiv  Detail & Related papers  (2023-11-23T08:01:18Z)
• When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks [17.243744418309593]
  We propose an efficient MIA method against fairness-enhanced models based on fairness discrepancy results. We also explore potential strategies for mitigating privacy leakages.
  arXiv  Detail & Related papers  (2023-11-07T10:28:17Z)
• Careful What You Wish For: on the Extraction of Adversarially Trained Models [2.707154152696381]
  Recent attacks on Machine Learning (ML) models pose several security and privacy threats. We propose a framework to assess extraction attacks on adversarially trained models. We show that adversarially trained models are more vulnerable to extraction attacks than models obtained under natural training circumstances.
  arXiv  Detail & Related papers  (2022-07-21T16:04:37Z)
• MEMO: Test Time Robustness via Adaptation and Augmentation [131.28104376280197]
  We study the problem of test time robustification, i.e., using the test input to improve model robustness. Recent prior works have proposed methods for test time adaptation, however, they each introduce additional assumptions. We propose a simple approach that can be used in any test setting where the model is probabilistic and adaptable.
  arXiv  Detail & Related papers  (2021-10-18T17:55:11Z)
• Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training [106.34722726264522]
  A range of adversarial defense techniques have been proposed to mitigate the interference of adversarial noise. Pre-processing methods may suffer from the robustness degradation effect. A potential cause of this negative effect is that adversarial training examples are static and independent to the pre-processing model. We propose a method called Joint Adversarial Training based Pre-processing (JATP) defense.
  arXiv  Detail & Related papers  (2021-06-10T01:45:32Z)
• Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
  CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength.
  arXiv  Detail & Related papers  (2021-05-31T17:01:05Z)
• Adversarial Distributional Training for Robust Deep Learning [53.300984501078126]
  Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. Most existing AT methods adopt a specific attack to craft adversarial examples, leading to the unreliable robustness against other unseen attacks. In this paper, we introduce adversarial distributional training (ADT), a novel framework for learning robust models.
  arXiv  Detail & Related papers  (2020-02-14T12:36:59Z)

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.