mlsanityData to 7 Oct 2026

Adversarial Attacks on Variational Autoencoders

arXiv 1806.04646 ↗First posted 12 Jun 2018cs.CV cs.LG cs.NEcited by 19

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correlates well with the qualitative assessment of the attacks. We assess --- with statistically validated experiments --- the resistance to attacks of three variational autoencoders (simple, convolutional, and DRAW) in three datasets (MNIST, SVHN, CelebA), showing that both DRAW's recurrence and attention mechanism lead to better resistance. As autoencoders are proposed for compressing data --- a scenario in which their safety is paramount --- we expect more attention will be given to adversarial attacks on them.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 3; 2023: 6; 2024: 2; 2025: 2; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 200
  2. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 22
  3. 2023Adversarial robustness of amortized Bayesian inferencecited by 17
  4. 2021Certifiably Robust Variational Autoencoderscited by 14
  5. 2024A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapsecited by 13
  6. 2022Alleviating Adversarial Attacks on Variational Autoencoders with MCMCcited by 10
  7. 2021Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Reviewcited by 8
  8. 2021Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attackscited by 7
  9. 2023Learning Hierarchical Features with Joint Latent Space Energy-Based Priorcited by 6
  10. 2022Adversarial robustness of VAEs through the lens of local geometrycited by 4
  11. 2021Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Trainingcited by 3
  12. 2023Adversarial Robustness in Unsupervised Machine Learning: A Systematic Reviewcited by 3
7 more
  1. 2022Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Futurecited by 1
  2. 2021MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysiscited by 0
  3. 2023On the Adversarial Robustness of Generative Autoencoders in the Latent Spacecited by 0
  4. 2023On Neural Network approximation of ideal adversarial attack and convergence of adversarial trainingcited by 0
  5. 2025Support is All You Need for Certified VAE Trainingcited by 0
  6. 2025Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restorationcited by 0
  7. 2026On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspacescited by 0