Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generation

• URL: http://arxiv.org/abs/2506.10685v3
• Date: Tue, 01 Jul 2025 17:49:09 GMT
• Title: Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generation
• Authors: Xia Du, Xiaoyuan Liu, Jizhe Zhou, Zheng Lin, Chi-man Pun, Cong Wu, Tao Li, Zhe Chen, Wei Ni, Jun Luo,
• Abstract summary: Traditional CAPTCHA schemes are increasingly vulnerable to automated attacks powered by deep neural networks (DNNs)<n>We propose the Unsourced Adversarial CAPTCHA (DAC), a novel framework that generates high-specified adversarial examples.<n>In untargeted attacks, especially for black-box scenarios, we introduce bi-path unsourced adversarial CAPTCHA (BP-DAC)
• Score: 48.60492738839292
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) schemes are increasingly vulnerable to automated attacks powered by deep neural networks (DNNs). Existing adversarial attack methods often rely on the original image characteristics, resulting in distortions that hinder human interpretation and limit their applicability in scenarios where no initial input images are available. To address these challenges, we propose the Unsourced Adversarial CAPTCHA (DAC), a novel framework that generates high-fidelity adversarial examples guided by attacker-specified semantics information. Leveraging a Large Language Model (LLM), DAC enhances CAPTCHA diversity and enriches the semantic information. To address various application scenarios, we examine the white-box targeted attack scenario and the black box untargeted attack scenario. For target attacks, we introduce two latent noise variables that are alternately guided in the diffusion step to achieve robust inversion. The synergy between gradient guidance and latent variable optimization achieved in this way ensures that the generated adversarial examples not only accurately align with the target conditions but also achieve optimal performance in terms of distributional consistency and attack effectiveness. In untargeted attacks, especially for black-box scenarios, we introduce bi-path unsourced adversarial CAPTCHA (BP-DAC), a two-step optimization strategy employing multimodal gradients and bi-path optimization for efficient misclassification. Experiments show that the defensive adversarial CAPTCHA generated by BP-DAC is able to defend against most of the unknown models, and the generated CAPTCHA is indistinguishable to both humans and DNNs.

Related papers

• MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks [7.293357145882387]
  MCA-Bench is a comprehensive and reproducible benchmarking suite.<n>It integrates heterogeneous CAPTCHA types into a single evaluation protocol.<n>Extensive experiments reveal that MCA-Bench effectively maps the vulnerability spectrum of modern CAPTCHA designs.
  arXiv  Detail & Related papers  (2025-06-06T11:02:01Z)
• Explainer-guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models [12.524811181751577]
  We propose a novel optimization for adversarial attacks against BCSD models.<n>In particular, we aim to improve the attacks in a challenging scenario, where the attack goal is to limit the model predictions to a specific range.<n>Our attack leverages the superior capability of black-box, model-agnostic explainers in interpreting the model decision boundaries.
  arXiv  Detail & Related papers  (2025-06-05T08:29:19Z)
• Input-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domain [0.0]
  An adversarial attack aims at finding a subtle input perturbation to fool the network's decision-making.<n>We propose two novel adversarial attack algorithms for Spiking Neural Networks (SNNs)<n> Experimental results on two widely used neuromorphic vision datasets, NMNIST and IBM DVS Gesture, show that our proposed attacks surpass in all metrics all existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-07T19:49:18Z)
• Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks [62.036798488144306]
  Current defense mainly focuses on the known attacks, but the adversarial robustness to the unknown attacks is seriously overlooked. We propose an attack-agnostic defense method named Meta Invariance Defense (MID) We show that MID simultaneously achieves robustness to the imperceptible adversarial perturbations in high-level image classification and attack-suppression in low-level robust image regeneration.
  arXiv  Detail & Related papers  (2024-04-04T10:10:38Z)
• Mutual-modality Adversarial Attack with Semantic Perturbation [81.66172089175346]
  We propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme. Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
  arXiv  Detail & Related papers  (2023-12-20T05:06:01Z)
• SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation [56.622250514119294]
  In contrast to white-box adversarial attacks, transfer attacks are more reflective of real-world scenarios. We propose a self-augment-based transfer attack method, termed SA-Attack.
  arXiv  Detail & Related papers  (2023-12-08T09:08:50Z)
• A Survey of Adversarial CAPTCHAs on its History, Classification and Generation [69.36242543069123]
  We extend the definition of adversarial CAPTCHAs and propose a classification method for adversarial CAPTCHAs. Also, we analyze some defense methods that can be used to defend adversarial CAPTCHAs, indicating potential threats to adversarial CAPTCHAs.
  arXiv  Detail & Related papers  (2023-11-22T08:44:58Z)
• Diff-CAPTCHA: An Image-based CAPTCHA with Security Enhanced by Denoising Diffusion Model [2.1551899143698328]
  Diff-CAPTCHA is an image-click CAPTCHA scheme based on diffusion models. This paper develops several attack methods, including end-to-end attacks based on Faster R-CNN and two-stage attacks. Results show that diffusion models can effectively enhance CAPTCHA security while maintaining good usability in human testing.
  arXiv  Detail & Related papers  (2023-08-16T13:41:29Z)
• Enhancing the Self-Universality for Transferable Targeted Attacks [88.6081640779354]
  Our new attack method is proposed based on the observation that highly universal adversarial perturbations tend to be more transferable for targeted attacks. Instead of optimizing the perturbations on different images, optimizing on different regions to achieve self-universality can get rid of using extra data. With the feature similarity loss, our method makes the features from adversarial perturbations to be more dominant than that of benign images.
  arXiv  Detail & Related papers  (2022-09-08T11:21:26Z)
• A Multi-objective Memetic Algorithm for Auto Adversarial Attack Optimization Design [1.9100854225243937]
  Well-designed adversarial defense strategies can improve the robustness of deep learning models against adversarial examples. Given the defensed model, the efficient adversarial attack with less computational burden and lower robust accuracy is needed to be further exploited. We propose a multi-objective memetic algorithm for auto adversarial attack optimization design, which realizes the automatical search for the near-optimal adversarial attack towards defensed models.
  arXiv  Detail & Related papers  (2022-08-15T03:03:05Z)
• Versatile Weight Attack via Flipping Limited Bits [68.45224286690932]
  We study a novel attack paradigm, which modifies model parameters in the deployment stage. Considering the effectiveness and stealthiness goals, we provide a general formulation to perform the bit-flip based weight attack. We present two cases of the general formulation with different malicious purposes, i.e., single sample attack (SSA) and triggered samples attack (TSA)
  arXiv  Detail & Related papers  (2022-07-25T03:24:58Z)
• Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust NIDS [0.3867363075280543]
  Adrial attacks pose a major threat to machine learning and to the systems that rely on it. This work introduces the Adaptative Perturbation Pattern Method (A2PM) to fulfill these constraints in a gray-box setting. A2PM relies on pattern sequences that are independently adapted to the characteristics of each class to create valid and coherent data perturbations.
  arXiv  Detail & Related papers  (2022-03-08T17:52:09Z)
• Robust Text CAPTCHAs Using Adversarial Examples [129.29523847765952]
  We propose a user-friendly text-based CAPTCHA generation method named Robust Text CAPTCHA (RTC) At the first stage, the foregrounds and backgrounds are constructed with randomly sampled font and background images. At the second stage, we apply a highly transferable adversarial attack for text CAPTCHAs to better obstruct CAPTCHA solvers.
  arXiv  Detail & Related papers  (2021-01-07T11:03:07Z)
• Double Targeted Universal Adversarial Perturbations [83.60161052867534]
  We introduce a double targeted universal adversarial perturbations (DT-UAPs) to bridge the gap between the instance-discriminative image-dependent perturbations and the generic universal perturbations. We show the effectiveness of the proposed DTA algorithm on a wide range of datasets and also demonstrate its potential as a physical attack.
  arXiv  Detail & Related papers  (2020-10-07T09:08:51Z)
• An End-to-End Attack on Text-based CAPTCHAs Based on Cycle-Consistent Generative Adversarial Network [4.955311532191887]
  We propose an efficient and simple end-to-end attack method based on cycle-consistent generative adversarial networks. It can attack common text-based CAPTCHA schemes only by modifying a few configuration parameters. Our approach efficiently cracked the CAPTCHA schemes deployed by 10 popular websites.
  arXiv  Detail & Related papers  (2020-08-26T14:57:47Z)
• A Self-supervised Approach for Adversarial Robustness [105.88250594033053]
  Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems. This paper proposes a self-supervised adversarial training mechanism in the input space. It provides significant robustness against the textbfunseen adversarial attacks.
  arXiv  Detail & Related papers  (2020-06-08T20:42:39Z)

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.