A New Type of Adversarial Examples

• URL: http://arxiv.org/abs/2510.19347v1
• Date: Wed, 22 Oct 2025 08:14:11 GMT
• Title: A New Type of Adversarial Examples
• Authors: Xingyang Nie, Guojie Xiao, Su Pan, Biao Wang, Huilin Ge, Tao Fang,
• Abstract summary: Adversarial examples are crafted by applying subtle but intentionally worst-case modifications to examples from the dataset.<n>We propose a novel set of algorithms to produce such adversarial examples.<n>Our results show that the adversarial examples are not merely distributed in the neighbourhood of the examples from the dataset.
• Score: 16.101504821305998
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most machine learning models are vulnerable to adversarial examples, which poses security concerns on these models. Adversarial examples are crafted by applying subtle but intentionally worst-case modifications to examples from the dataset, leading the model to output a different answer from the original example. In this paper, adversarial examples are formed in an exactly opposite manner, which are significantly different from the original examples but result in the same answer. We propose a novel set of algorithms to produce such adversarial examples, including the negative iterative fast gradient sign method (NI-FGSM) and the negative iterative fast gradient method (NI-FGM), along with their momentum variants: the negative momentum iterative fast gradient sign method (NMI-FGSM) and the negative momentum iterative fast gradient method (NMI-FGM). Adversarial examples constructed by these methods could be used to perform an attack on machine learning systems in certain occasions. Moreover, our results show that the adversarial examples are not merely distributed in the neighbourhood of the examples from the dataset; instead, they are distributed extensively in the sample space.

Related papers

• Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples [74.60723854735237]
  We show that mislabeled examples correctly predicted by the model early in the training process are particularly harmful to model performance.<n>We propose Early Cutting, which employs the model's later training state to re-select the confident subset identified early in training.
  arXiv  Detail & Related papers  (2025-02-12T09:12:45Z)
• Reversible Jump Attack to Textual Classifiers with Modification Reduction [8.247761405798874]
  Reversible Jump Attack (RJA) and Metropolis-Hasting Modification Reduction (MMR) are proposed. RJA-MMR outperforms current state-of-the-art methods in attack performance, imperceptibility, fluency and grammar correctness.
  arXiv  Detail & Related papers  (2024-03-21T04:54:31Z)
• Late Stopping: Avoiding Confidently Learning from Mislabeled Examples [61.00103151680946]
  We propose a new framework, Late Stopping, which leverages the intrinsic robust learning ability of DNNs through a prolonged training process. We empirically observe that mislabeled and clean examples exhibit differences in the number of epochs required for them to be consistently and correctly classified. Experimental results on benchmark-simulated and real-world noisy datasets demonstrate that the proposed method outperforms state-of-the-art counterparts.
  arXiv  Detail & Related papers  (2023-08-26T12:43:25Z)
• 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)
• The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training [72.39526433794707]
  Adversarial training and its variants have been shown to be the most effective approaches to defend against adversarial examples. We propose a novel adversarial training scheme that encourages the model to produce similar outputs for an adversarial example and its inverse adversarial'' counterpart. Our training method achieves state-of-the-art robustness as well as natural accuracy.
  arXiv  Detail & Related papers  (2022-11-01T15:24:26Z)
• Adversarial Examples on Segmentation Models Can be Easy to Transfer [21.838878497660353]
  The transferability of adversarial examples on classification models has attracted a growing interest. We study the overfitting phenomenon of adversarial examples on classification and segmentation models. We propose a simple and effective method, dubbed dynamic scaling, to overcome the limitation.
  arXiv  Detail & Related papers  (2021-11-22T17:26:21Z)
• Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations [16.346349209014182]
  Studies show that neural networks are susceptible to adversarial attacks. This exposes a potential threat to neural network-based intelligent systems. We propose a method for counteracting adversarial perturbations to improve adversarial robustness.
  arXiv  Detail & Related papers  (2021-03-08T06:27:24Z)
• Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions [16.993439721743478]
  The proposed method is based on the observation that the directions of adversarial gradients play a key role in characterizing the adversarial space. Experiments conducted on two different databases, CIFAR-10 and ImageNet, show that the proposed detection method achieves 97.9% and 98.6% AUC-ROC on five different adversarial attacks.
  arXiv  Detail & Related papers  (2020-12-31T01:12:24Z)
• On the Transferability of Adversarial Attacksagainst Neural Text Classifier [121.6758865857686]
  We investigate the transferability of adversarial examples for text classification models. We propose a genetic algorithm to find an ensemble of models that can induce adversarial examples to fool almost all existing models. We derive word replacement rules that can be used for model diagnostics from these adversarial examples.
  arXiv  Detail & Related papers  (2020-11-17T10:45:05Z)
• Robust and On-the-fly Dataset Denoising for Image Classification [72.10311040730815]
  On-the-fly Data Denoising (ODD) is robust to mislabeled examples, while introducing almost zero computational overhead compared to standard training. ODD is able to achieve state-of-the-art results on a wide range of datasets including real-world ones such as WebVision and Clothing1M.
  arXiv  Detail & Related papers  (2020-03-24T03:59:26Z)
• Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations [65.05561023880351]
  Adversarial examples are malicious inputs crafted to induce misclassification. This paper studies a complementary failure mode, invariance-based adversarial examples. We show that defenses against sensitivity-based attacks actively harm a model's accuracy on invariance-based attacks.
  arXiv  Detail & Related papers  (2020-02-11T18:50:23Z)

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.