mlsanityData to 7 Oct 2026

Privacy and Security Implications of Cloud-Based AI Services : A Survey

arXiv 2402.00896 ↗First posted 31 Jan 2024cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper details the privacy and security landscape in today's cloud ecosystem and identifies that there is a gap in addressing the risks introduced by machine learning models. As machine learning algorithms continue to evolve and find applications across diverse domains, the need to categorize and quantify privacy and security risks becomes increasingly critical. With the emerging trend of AI-as-a-Service (AIaaS), machine learned AI models (or ML models) are deployed on the cloud by model providers and used by model consumers. We first survey the AIaaS landscape to document the various kinds of liabilities that ML models, especially Deep Neural Networks pose and then introduce a taxonomy to bridge this gap by holistically examining the risks that creators and consumers of ML models are exposed to and their known defences till date. Such a structured approach will be beneficial for ML model providers to create robust solutions. Likewise, ML model consumers will find it valuable to evaluate such solutions and understand the implications of their engagement with such services. The proposed taxonomies provide a foundational basis for solutions in private, secure and robust ML, paving the way for more transparent and resilient AI systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 70 references that are in the map. First posted on arXiv 31 Jan 2024.

Builds on

35 of 70 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  6. 2017Federated Multi-Task Learningcited by 669
  7. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  8. 2020Label-Only Membership Inference Attackscited by 371
  9. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  10. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  11. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  12. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
23 more
  1. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
  2. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 154
  3. 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 129
  4. 2018Stronger Data Poisoning Attacks Break Data Sanitization Defensescited by 125
  5. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  6. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  7. 2019BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learningcited by 115
  8. 2017Deep Voice: Real-time Neural Text-to-Speechcited by 83
  9. 2020When Machine Learning Meets Privacy: A Survey and Outlookcited by 67
  10. 2018Backdooring Convolutional Neural Networks via Targeted Weight Perturbationscited by 66
  11. 2021Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Networkcited by 57
  12. 2023Assessing Prompt Injection Risks in 200+ Custom GPTscited by 49
  13. 2022SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learningcited by 47
  14. 2023Reinforcement Learning-Based Black-Box Model Inversion Attackscited by 33
  15. 2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
  16. 2021ML Attack Models: Adversarial Attacks and Data Poisoning Attackscited by 23
  17. 2021A Novel Attribute Reconstruction Attack in Federated Learningcited by 18
  18. 2023Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learningcited by 15
  19. 2022Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition Systemcited by 9
  20. 2023Investigating the Effect of Misalignment on Membership Privacy in the White-box Settingcited by 9
  21. 2023Adversarial Attacks on the Interpretation of Neuron Activation Maximizationcited by 7
  22. 2020Black-box Model Inversion Attribute Inference Attacks on Classification Modelscited by 6
  23. 2022Local Model Reconstruction Attacks in Federated Learning and their Usescited by 2

Built on by

Not cited yet.