mlsanityData to 14 Oct 2026

OFEI: A Semi-black-box Android Adversarial Sample Attack Framework Against DLaaS

arXiv 2105.11593 ↗First posted 25 May 2021cs.CR cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

With the growing popularity of Android devices, Android malware is seriously threatening the safety of users. Although such threats can be detected by deep learning as a service (DLaaS), deep neural networks as the weakest part of DLaaS are often deceived by the adversarial samples elaborated by attackers. In this paper, we propose a new semi-black-box attack framework called one-feature-each-iteration (OFEI) to craft Android adversarial samples. This framework modifies as few features as possible and requires less classifier information to fool the classifier. We conduct a controlled experiment to evaluate our OFEI framework by comparing it with the benchmark methods JSMF, GenAttack and pointwise attack. The experimental results show that our OFEI has a higher misclassification rate of 98.25%. Furthermore, OFEI can extend the traditional white-box attack methods in the image field, such as fast gradient sign method (FGSM) and DeepFool, to craft adversarial samples for Android. Finally, to enhance the security of DLaaS, we use two uncertainties of the Bayesian neural network to construct the combined uncertainty, which is used to detect adversarial samples and achieves a high detection rate of 99.28%.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 25 May 2021.

Builds on

21 of 37 references.

References · 21

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  6. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  7. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  8. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
  9. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  10. 2017Detecting Adversarial Samples from Artifactscited by 245
  11. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  12. 2020An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Modelscited by 68
9 more
  1. 2016Adversarial Perturbations Against Deep Neural Networks for Malware Classificationcited by 42
  2. 2017Google's Cloud Vision API Is Not Robust To Noisecited by 37
  3. 2020Adversarial Deep Ensemble: Evasion Attacks and Defenses for Malware Detectioncited by 33
  4. 2018Adversarial Deep Learning for Robust Detection of Binary Encoded Malwarecited by 32
  5. 2020A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networkscited by 7
  6. 2017Query-Efficient Black-box Adversarial Examples (superceded)cited by 5
  7. 2018A Review on The Use of Deep Learning in Android Malware Detectioncited by 5
  8. 2020Attacking and Defending Machine Learning Applications of Public Cloudcited by 3
  9. 2020Transferability of Adversarial Examples to Attack Cloud-based Image Classifier Servicecited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 2; 2025: 1.

7 papers.

  1. 2021EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware Detectioncited by 13
  2. 2024A Survey of Malware Detection Using Deep Learningcited by 9
  3. 2023MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attackscited by 3
  4. 2022Level Up with ML Vulnerability Identification: Leveraging Domain Constraints in Feature Space for Robust Android Malware Detectioncited by 2
  5. 2024On the Effectiveness of Adversarial Training on Malware Classifierscited by 1
  6. 2025On the Security Risks of ML-based Malware Detection Systems: A Surveycited by 1
  7. 2022Adversarial Patterns: Building Robust Android Malware Classifierscited by 0