mlsanityData to 7 Oct 2026

Security and Privacy for Artificial Intelligence: Opportunities and Challenges

arXiv 2102.04661 ↗First posted 9 Feb 2021cs.CR cs.AIcited by 16

Not on the map. Why?

Abstract (arXiv)

The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models are vulnerable to advanced and sophisticated hacking techniques. This challenge has motivated concerted research efforts into adversarial AI, with the aim of developing robust machine and deep learning models that are resilient to different types of adversarial scenarios. In this paper, we present a holistic cyber security review that demonstrates adversarial attacks against AI applications, including aspects such as adversarial knowledge and capabilities, as well as existing methods for generating adversarial examples and existing cyber defence models. We explain mathematical AI models, especially new variants of reinforcement and federated learning, to demonstrate how attack vectors would exploit vulnerabilities of AI models. We also propose a systematic framework for demonstrating attack techniques against AI applications and reviewed several cyber defences that would protect AI applications against those attacks. We also highlight the importance of understanding the adversarial goals and their capabilities, especially the recent attacks against industry applications, to develop adaptive defences that assess to secure AI applications. Finally, we describe the main challenges and future research directions in the domain of security and privacy of AI technologies.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 73 of its 139 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

73 of 139 references.

References · 73

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  8. 2016Adversarial examples in the physical worldcited by 1,762
  9. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  12. 2016Adversarial Machine Learning at Scalecited by 934
38 more
  1. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  2. 2019Towards Federated Learning at Scale: System Designcited by 826
  3. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  4. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  5. 2016Universal adversarial perturbationscited by 774
  6. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  7. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  8. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  9. 2019Adversarial Training for Free!cited by 638
  10. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  11. 2017One pixel attack for fooling deep neural networkscited by 579
  12. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  13. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  14. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  15. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  16. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  17. 2013Do Deep Nets Really Need to be Deep?cited by 466
  18. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  19. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  20. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  21. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  22. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  23. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  24. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  25. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  26. 2018Adversarial Attacks and Defences: A Surveycited by 259
  27. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  28. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 188
  29. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  30. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  31. 2017The Space of Transferable Adversarial Examplescited by 156
  32. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
  33. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  34. 2018Stronger Data Poisoning Attacks Break Data Sanitization Defensescited by 125
  35. 2016Data Poisoning Attacks on Factorization-Based Collaborative Filteringcited by 78
  36. 2018Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attackscited by 78
  37. 2017Generating Adversarial Malware Examples for Black-Box Attacks Based on GANcited by 74
  38. 2018Adversarial Examples: Opportunities and Challengescited by 62

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 0; 2024: 5; 2025: 6; 2026: 2.

16 papers.

Sort:

By area:

  1. 2022AI Ethics Issues in Real World: Evidence from AI Incident Databasecited by 14
  2. 2022Progressive Cross-modal Knowledge Distillation for Human Action Recognitioncited by 6
  3. 2024Sensitive Content Classification in Social Media: A Holistic Resource and Evaluationcited by 4
  4. 2024AntibotV: A Multilevel Behaviour-based Framework for Botnets Detection in Vehicular Networkscited by 3
  5. 2024The AI Security Pyramid of Paincited by 2
  6. 2024Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognitioncited by 1
  7. 2024SoK: Towards Security and Safety of Edge AIcited by 1
  8. 2025Securing AI Systems: A Guide to Known Attacks and Impactscited by 1
  9. 2022Artificial Intelligence Nomenclature Identified From Delphi Study on Key Issues Related to Trust and Barriers to Adoption for Autonomous Systemscited by 0
  10. 2025Detecting underdetermination in parameterized quantum circuitscited by 0
  11. 2025Mechanistic Interpretability in the Presence of Architectural Obfuscationcited by 0
  12. 2025LLM-Guided Synthetic Augmentation (LGSA) for Mitigating Bias in AI Systemscited by 0
4 more
  1. 2025Android Malware Detection: A Machine Leaning Approachcited by 0
  2. 2025Optimizing Agricultural Research: A RAG-Based Approach to Mycorrhizal Fungi Informationcited by 0
  3. 2026From Performance to Purpose: A Sociotechnical Taxonomy for Evaluating Large Language Model Utilitycited by 0
  4. 2026Artificial Intelligence and Innovation Ecosystem: Evolutionary Developments, Challenges, and Future Directionscited by 0