mlsanityData to 7 Oct 2026

BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection

arXiv 2412.13324 ↗First posted 17 Dec 2024cs.CV cs.AI cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Image anomaly detection (IAD) is essential in applications such as industrial inspection, medical imaging, and security. Despite the progress achieved with deep learning models like Deep Semi-Supervised Anomaly Detection (DeepSAD), these models remain susceptible to backdoor attacks, presenting significant security challenges. In this paper, we introduce BadSAD, a novel backdoor attack framework specifically designed to target DeepSAD models. Our approach involves two key phases: trigger injection, where subtle triggers are embedded into normal images, and latent space manipulation, which positions and clusters the poisoned images near normal images to make the triggers appear benign. Extensive experiments on benchmark datasets validate the effectiveness of our attack strategy, highlighting the severe risks that backdoor attacks pose to deep learning-based anomaly detection systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 17 Dec 2024.

Builds on

21 of 33 references.

References · 21

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  3. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  4. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  5. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  6. 2020Backdoor Learning: A Surveycited by 412
  7. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  8. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  9. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 338
  10. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  11. 2022Diffusion Models for Medical Anomaly Detectioncited by 231
  12. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
9 more
  1. 2020Deep Learning for Anomaly Detection: A Reviewcited by 159
  2. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  3. 2020Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Reviewcited by 120
  4. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 110
  5. 2022Narcissus: A Practical Clean-Label Backdoor Attack with Limited Informationcited by 102
  6. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  7. 2021Poison Ink: Robust and Invisible Backdoor Attackcited by 50
  8. 2024Supervised Anomaly Detection for Complex Industrial Imagescited by 18
  9. 2024Backdoor Attack against One-Class Sequential Anomaly Detection Modelscited by 1

Built on by

Not cited yet.