mlsanityData to 14 Oct 2026

AI-GAN: Attack-Inspired Generation of Adversarial Examples

arXiv 2002.02196 ↗First posted 6 Feb 2020cs.LG cs.CR stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding imperceptible perturbations to inputs. Recently different attacks and strategies have been proposed, but how to generate adversarial examples perceptually realistic and more efficiently remains unsolved. This paper proposes a novel framework called Attack-Inspired GAN (AI-GAN), where a generator, a discriminator, and an attacker are trained jointly. Once trained, it can generate adversarial perturbations efficiently given input images and target classes. Through extensive experiments on several popular datasets eg MNIST and CIFAR-10, AI-GAN achieves high attack success rates and reduces generation time significantly in various settings. Moreover, for the first time, AI-GAN successfully scales to complicated datasets eg CIFAR-100 with around 90% success rates among all classes.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 2; 2023: 6; 2024: 9; 2025: 1; 2026: 1.

22 papers.

Sort:

By area:

  1. 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 61
  2. 2022Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generatorcited by 5
  3. 2024Generating Universal Adversarial Perturbations for Quantum Classifierscited by 5
  4. 2021Synthetic flow-based cryptomining attack generation through Generative Adversarial Networkscited by 4
  5. 2023Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Modelscited by 4
  6. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  7. 2023Evading Detection Actively: Toward Anti-Forensics against Forgery Localizationcited by 1
  8. 2024SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledgecited by 1
  9. 2024Deep generative models as an adversarial attack strategy for tabular machine learningcited by 1
  10. 2021Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognitioncited by 0
  11. 2021Using a GAN to Generate Adversarial Examples to Facial Image Recognitioncited by 0
  12. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
10 more
  1. 2023GMTR: Graph Matching Transformerscited by 0
  2. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  3. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  4. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  5. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  6. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  7. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  8. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  9. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  10. 2026Attack Assessment and Augmented Identity Recognition for Human Skeleton Datacited by 0