A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection

• URL: http://arxiv.org/abs/2505.12586v4
• Date: Fri, 13 Jun 2025 14:43:47 GMT
• Title: A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection
• Authors: Sanggeon Yun, Ryozo Masukawa, Hyunwoo Oh, Nathaniel D. Bastian, Mohsen Imani,
• Abstract summary: We introduce a lightweight, plug-in detection framework that leverages internal layer-wise inconsistencies within the target model itself.<n>Our method achieves state-of-the-art detection performance with negligible computational overhead and no compromise to clean accuracy.
• Score: 9.335304254034401
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle, imperceptible perturbations that can lead to incorrect predictions. While detection-based defenses offer a practical alternative to adversarial training, many existing methods depend on external models, complex architectures, heavy augmentations, or adversarial data, limiting their efficiency and generalizability. We introduce a lightweight, plug-in detection framework that leverages internal layer-wise inconsistencies within the target model itself, requiring only benign data for calibration. Our approach is grounded in the A Few Large Shifts Assumption, which posits that adversarial perturbations typically induce large representation shifts in a small subset of layers. Building on this, we propose two complementary strategies--Recovery Testing (RT) and Logit-layer Testing (LT)--to expose internal disruptions caused by adversaries. Evaluated on CIFAR-10, CIFAR-100, and ImageNet under both standard and adaptive threat models, our method achieves state-of-the-art detection performance with negligible computational overhead and no compromise to clean accuracy. The code is available here: https://github.com/c0510gy/AFLS-AED.

Related papers

• Universal and Efficient Detection of Adversarial Data through Nonuniform Impact on Network Layers [24.585379549997743]
  Deep Neural Networks (DNNs) are notoriously vulnerable to adversarial input designs with limited noise budgets.<n>We show that the existing detection methods are either ineffective against the state-of-the-art attack techniques or computationally inefficient for real-time processing.<n>We propose a novel universal and efficient method to detect adversarial examples by analyzing the varying degrees of impact of attacks on different DNN layers.
  arXiv  Detail & Related papers  (2025-06-25T20:30:28Z)
• Pulling Back the Curtain: Unsupervised Adversarial Detection via Contrastive Auxiliary Networks [0.0]
  We propose an Unsupervised adversarial detection via Auxiliary Contrastive Networks (U-CAN) to uncover adversarial behavior within auxiliary feature representations.<n>Our method surpasses existing unsupervised adversarial detection techniques, achieving superior F1 scores against four distinct attack methods.
  arXiv  Detail & Related papers  (2025-02-13T09:40:26Z)
• Advancing Adversarial Robustness Through Adversarial Logit Update [10.041289551532804]
  Adversarial training and adversarial purification are among the most widely recognized defense strategies. We propose a new principle, namely Adversarial Logit Update (ALU), to infer adversarial sample's labels. Our solution achieves superior performance compared to state-of-the-art methods against a wide range of adversarial attacks.
  arXiv  Detail & Related papers  (2023-08-29T07:13:31Z)
• Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization [20.132066800052712]
  We propose an adversarial example detection framework based on a high-frequency information enhancement strategy. This framework can effectively extract and amplify the feature differences between adversarial examples and normal examples.
  arXiv  Detail & Related papers  (2023-05-08T03:14:01Z)
• Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning [80.21709045433096]
  A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample. We use metric learning to frame adversarial regularization as an optimal transport problem. Our preliminary results indicate that regularizing over invariant perturbations in our framework improves both invariant and sensitivity defense.
  arXiv  Detail & Related papers  (2022-11-04T13:54:02Z)
• Improved and Interpretable Defense to Transferred Adversarial Examples by Jacobian Norm with Selective Input Gradient Regularization [31.516568778193157]
  Adversarial training (AT) is often adopted to improve the robustness of deep neural networks (DNNs) In this work, we propose an approach based on Jacobian norm and Selective Input Gradient Regularization (J- SIGR) Experiments demonstrate that the proposed J- SIGR confers improved robustness against transferred adversarial attacks, and we also show that the predictions from the neural network are easy to interpret.
  arXiv  Detail & Related papers  (2022-07-09T01:06:41Z)
• Latent Boundary-guided Adversarial Training [61.43040235982727]
  Adrial training is proved to be the most effective strategy that injects adversarial examples into model training. We propose a novel adversarial training framework called LAtent bounDary-guided aDvErsarial tRaining.
  arXiv  Detail & Related papers  (2022-06-08T07:40:55Z)
• Discriminator-Free Generative Adversarial Attack [87.71852388383242]
  Agenerative-based adversarial attacks can get rid of this limitation. ASymmetric Saliency-based Auto-Encoder (SSAE) generates the perturbations. The adversarial examples generated by SSAE not only make thewidely-used models collapse, but also achieves good visual quality.
  arXiv  Detail & Related papers  (2021-07-20T01:55:21Z)
• Combating Adversaries with Anti-Adversaries [118.70141983415445]
  In particular, our layer generates an input perturbation in the opposite direction of the adversarial one. We verify the effectiveness of our approach by combining our layer with both nominally and robustly trained models. Our anti-adversary layer significantly enhances model robustness while coming at no cost on clean accuracy.
  arXiv  Detail & Related papers  (2021-03-26T09:36:59Z)
• Attribute-Guided Adversarial Training for Robustness to Natural Perturbations [64.35805267250682]
  We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
  arXiv  Detail & Related papers  (2020-12-03T10:17:30Z)
• FADER: Fast Adversarial Example Rejection [19.305796826768425]
  Recent defenses have been shown to improve adversarial robustness by detecting anomalous deviations from legitimate training samples at different layer representations. We introduce FADER, a novel technique for speeding up detection-based methods. Our experiments outline up to 73x prototypes reduction compared to analyzed detectors for MNIST dataset and up to 50x for CIFAR10 respectively.
  arXiv  Detail & Related papers  (2020-10-18T22:00:11Z)
• A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning [122.49765136434353]
  We present an effective method, called Hamiltonian Monte Carlo with Accumulated Momentum (HMCAM), aiming to generate a sequence of adversarial examples. We also propose a new generative method called Contrastive Adversarial Training (CAT), which approaches equilibrium distribution of adversarial examples. Both quantitative and qualitative analysis on several natural image datasets and practical systems have confirmed the superiority of the proposed algorithm.
  arXiv  Detail & Related papers  (2020-10-15T16:07:26Z)
• 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.