mlsanityData to 7 Oct 2026

Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution Detection

arXiv 2206.07321 ↗First posted 15 Jun 2022cs.CR cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Evasion attacks against machine learning models often succeed via iterative probing of a fixed target model, whereby an attack that succeeds once will succeed repeatedly. One promising approach to counter this threat is making a model a moving target against adversarial inputs. To this end, we introduce Morphence-2.0, a scalable moving target defense (MTD) powered by out-of-distribution (OOD) detection to defend against adversarial examples. By regularly moving the decision function of a model, Morphence-2.0 makes it significantly challenging for repeated or correlated attacks to succeed. Morphence-2.0 deploys a pool of models generated from a base model in a manner that introduces sufficient randomness when it responds to prediction queries. Via OOD detection, Morphence-2.0 is equipped with a scheduling approach that assigns adversarial examples to robust decision functions and benign samples to an undefended accurate models. To ensure repeated or correlated attacks fail, the deployed pool of models automatically expires after a query budget is reached and the model pool is seamlessly replaced by a new model pool generated in advance. We evaluate Morphence-2.0 on two benchmark image classification datasets (MNIST and CIFAR10) against 4 reference attacks (3 white-box and 1 black-box). Morphence-2.0 consistently outperforms prior defenses while preserving accuracy on clean data and reducing attack transferability. We also show that, when powered by OOD detection, Morphence-2.0 is able to precisely make an input-based movement of the model's decision function that leads to higher prediction accuracy on both adversarial and benign queries.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 53 references that are in the map. First posted on arXiv 15 Jun 2022.

Builds on

40 of 53 references.

References · 40

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  5. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  6. 2016Adversarial Machine Learning at Scalecited by 934
  7. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  8. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  9. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  10. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  11. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  12. 2017Countering Adversarial Images using Input Transformationscited by 517
28 more
  1. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  2. 2019On Evaluating Adversarial Robustnesscited by 442
  3. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  4. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  5. 2018Certified Defenses against Adversarial Examplescited by 305
  6. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  7. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  8. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  9. 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
  10. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  11. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  12. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  13. 2017Malware Detection by Eating a Whole EXEcited by 114
  14. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 86
  15. 2017Generating Adversarial Malware Examples for Black-Box Attacks Based on GANcited by 74
  16. 2018Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Datacited by 69
  17. 2015Learning with a Strong Adversarycited by 68
  18. 2018Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executablescited by 60
  19. 2017Efficient Defenses Against Adversarial Attackscited by 53
  20. 2017Enhancing Robustness of Machine Learning Systems via Data Transformationscited by 38
  21. 2015Foveation-based Mechanisms Alleviate Adversarial Examplescited by 32
  22. 2017Adversarial Example Defenses: Ensembles of Weak Defenses are not Strongcited by 32
  23. 2019A Research Agenda: Dynamic Models to Defend Against Correlated Attackscited by 18
  24. 2017MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defensecited by 12
  25. 2021Morphence: Moving Target Defense Against Adversarial Examplescited by 9
  26. 2019Moving Target Defense for Deep Visual Sensing against Adversarial Examplescited by 7
  27. 2020EI-MTD:Moving Target Defense for Edge Intelligence against Adversarial Attackscited by 6
  28. 2022Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problemcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customizationcited by 2
  2. 2026MorphStrata: Layer-Specific Perturbations for Generating Morphence Students in Time-Series Moving Target Defensecited by 0