paper-with-me

홈 › Papers

Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review

2023-06-01 · Mathias Lundteigen Mohus, Jinyue Li

As the adoption of machine learning models increases, ensuring robust models against adversarial attacks is increasingly important. With unsupervised machine learning gaining more attention, ensuring it is robust against attacks is vital. This paper conducts a systematic literature review on the robustness of unsupervised learning, collecting 86 papers. Our results show that most research focuses on privacy attacks, which have effective defenses; however, many attacks lack effective and general defensive measures. Based on the results, we formulate a model on the properties of an attack on unsupervised learning, contributing to future research by providing a model to use.

📄 PDF Abstract BibTeX arXiv:2306.00687

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessSystematic Literature Review

Similar Papers 제목 키워드 기반

A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?

2021-12-01 · Nathan Drenkow, Numair Sani, Ilya Shpitser, Mathias Unberath

Deep neural networks for computer vision are deployed in increasingly safety-critical and socially-impactful applications, motivating the need to close the gap in model performance under varied, naturally occurring imagi…

Adversarial RobustnessData AugmentationNon-Adversarial Robustness

Adversarial Defense in Cybersecurity: A Systematic Review of GANs for Threat Detection and Mitigation

2025-09-24 · Tharcisse Ndayipfukamiye, Jianguo Ding, Doreen Sebastian Sarwatt, Adamu Gaston Philipo 외 arxiv

Machine learning-based cybersecurity systems are highly vulnerable to adversarial attacks, while Generative Adversarial Networks (GANs) act as both powerful attack enablers and promising defenses. This survey systematica…

Network Intrusion DetectionAdversarial Defense

A Tour of Unsupervised Deep Learning for Medical Image Analysis

2018-12-19 · Khalid Raza, Nripendra Kumar Singh

Interpretation of medical images for diagnosis and treatment of complex disease from high-dimensional and heterogeneous data remains a key challenge in transforming healthcare. In the last few years, both supervised and …

Deep LearningGenerative Adversarial NetworkMedical Image Analysis

On the Robustness of Domain Adaption to Adversarial Attacks

2021-08-04 · Liyuan Zhang, YuHang Zhou, Lei Zhang

State-of-the-art deep neural networks (DNNs) have been proved to have excellent performance on unsupervised domain adaption (UDA). However, recent work shows that DNNs perform poorly when being attacked by adversarial sa…

Adversarial AttackDomain AdaptationPseudo LabelUnsupervised Domain Adaptation

Adversarial Examples in Environment Perception for Automated Driving (Review)

2025-04-11 · Jun Yan, Huilin Yin

The renaissance of deep learning has led to the massive development of automated driving. However, deep neural networks are vulnerable to adversarial examples. The perturbations of adversarial examples are imperceptible …

Adversarial Robustness