mlsanityData to 7 Oct 2026

Double Targeted Universal Adversarial Perturbations

arXiv 2010.03288 ↗First posted 7 Oct 2020cs.LG cs.CR cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Despite their impressive performance, deep neural networks (DNNs) are widely known to be vulnerable to adversarial attacks, which makes it challenging for them to be deployed in security-sensitive applications, such as autonomous driving. Image-dependent perturbations can fool a network for one specific image, while universal adversarial perturbations are capable of fooling a network for samples from all classes without selection. 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. This universal perturbation attacks one targeted source class to sink class, while having a limited adversarial effect on other non-targeted source classes, for avoiding raising suspicions. Targeting the source and sink class simultaneously, we term it double targeted attack (DTA). This provides an attacker with the freedom to perform precise attacks on a DNN model while raising little suspicion. We show the effectiveness of the proposed DTA algorithm on a wide range of datasets and also demonstrate its potential as a physical attack.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 10; 2023: 3; 2024: 1; 2025: 2.

23 papers.

Sort:

By area:

  1. 2021A Survey On Universal Adversarial Attackcited by 59
  2. 2021Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNscited by 57
  3. 2022ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patchescited by 27
  4. 2022Investigating Top-k White-Box and Transferable Black-box Attackcited by 26
  5. 2022Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustnesscited by 20
  6. 2021Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspectivecited by 18
  7. 2021Universal Adversarial Training with Class-Wise Perturbationscited by 13
  8. 2022Imperceptible Adversarial Attack via Invertible Neural Networkscited by 12
  9. 2022Visual Adversarial Attacks and Defenses in the Physical World: A Surveycited by 11
  10. 2021Semantically Stealthy Adversarial Attacks against Segmentation Modelscited by 7
  11. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  12. 2023SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbationcited by 4
11 more
  1. 2025Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimizationcited by 3
  2. 2022Optimization Models and Interpretations for Three Types of Adversarial Perturbations against Support Vector Machinescited by 2
  3. 2022Robust Universal Adversarial Perturbationscited by 2
  4. 2024Edge-Only Universal Adversarial Attacks in Distributed Learningcited by 2
  5. 2021On Distinctive Properties of Universal Perturbationscited by 1
  6. 2022Real-time Over-the-air Adversarial Perturbations for Digital Communications using Deep Neural Networkscited by 1
  7. 2022Unifying Gradients to Improve Real-world Robustness for Deep Networkscited by 1
  8. 2022SAIF: Sparse Adversarial and Imperceptible Attack Frameworkcited by 1
  9. 2023Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithmcited by 1
  10. 2025Democratic Training Against Universal Adversarial Perturbationscited by 1
  11. 2021Resilience of Autonomous Vehicle Object Category Detection to Universal Adversarial Perturbationscited by 0