mlsanityData to 14 Oct 2026

Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attacks

arXiv 2105.03251 ↗First posted 5 May 2021cs.CR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

From tiny pacemaker chips to aircraft collision avoidance systems, the state-of-the-art Cyber-Physical Systems (CPS) have increasingly started to rely on Deep Neural Networks (DNNs). However, as concluded in various studies, DNNs are highly susceptible to security threats, including adversarial attacks. In this paper, we first discuss different vulnerabilities that can be exploited for generating security attacks for neural network-based systems. We then provide an overview of existing adversarial and fault-injection-based attacks on DNNs. We also present a brief analysis to highlight different challenges in the practical implementation of adversarial attacks. Finally, we also discuss various prospective ways to develop robust DNN-based systems that are resilient to adversarial and fault-injection attacks.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 44 of its 70 references that are in the map. First posted on arXiv 5 May 2021.

Builds on

44 of 70 references.

References · 44

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2016Adversarial examples in the physical worldcited by 1,769
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  7. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  8. 2016Universal adversarial perturbationscited by 784
  9. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  10. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  11. 2017One pixel attack for fooling deep neural networkscited by 582
  12. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
32 more
  1. 2017Adversarial Patchcited by 517
  2. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  3. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  4. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  5. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
  6. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225
  7. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 155
  8. 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 151
  9. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 147
  10. 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 131
  11. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
  12. 2019Bit-Flip Attack: Crushing Neural Network with Progressive Bit Searchcited by 108
  13. 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 104
  14. 2019Wasserstein Adversarial Examples via Projected Sinkhorn Iterationscited by 89
  15. 2015Adversarial Manipulation of Deep Representationscited by 56
  16. 2016Simple Black-Box Adversarial Perturbations for Deep Networkscited by 42
  17. 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 41
  18. 2019FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activationcited by 31
  19. 2019Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networkscited by 26
  20. 2019A geometry-inspired decision-based attackcited by 22
  21. 2018QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attackscited by 21
  22. 2020Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificatescited by 18
  23. 2018Adversarial Attacks for Optical Flow-Based Action Recognition Classifierscited by 14
  24. 2018The Limitations of Model Uncertainty in Adversarial Settingscited by 14
  25. 2017Linearized ADMM for Non-convex Non-smooth Optimization with Convergence Analysiscited by 12
  26. 2018CSI Neural Network: Using Side-channels to Recover Your Artificial Neural Network Informationcited by 9
  27. 2018TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networkscited by 8
  28. 2018FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learningcited by 7
  29. 2019FANNet: Formal Analysis of Noise Tolerance, Training Bias and Input Sensitivity in Neural Networkscited by 7
  30. 2020A Low-cost Fault Corrector for Deep Neural Networks through Range Restrictioncited by 5
  31. 2018SSCNets: Robustifying DNNs using Secure Selective Convolutional Filterscited by 4
  32. 2019Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attackscited by 3

Built on by

Cited by year

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

4 papers.

  1. 2023Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5's Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lackingcited by 7
  2. 2025Verification of Bit-Flip Attacks against Quantized Neural Networkscited by 2
  3. 2023Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version)cited by 0
  4. 2024AdvSecureNet: A Python Toolkit for Adversarial Machine Learningcited by 0