mlsanityData to 7 Oct 2026

Deep Learning Model Security: Threats and Defenses

arXiv 2412.08969 ↗First posted 12 Dec 2024cs.CR cs.LG cs.SEcited by 4

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms and impact on model integrity and confidentiality. Practical implementations, including adversarial examples, label flipping, and backdoor attacks, are explored alongside defenses such as adversarial training, differential privacy, and federated learning, highlighting their strengths and limitations. Advanced methods like contrastive and self-supervised learning are presented for enhancing robustness. The survey concludes with future directions, emphasizing automated defenses, zero-trust architectures, and the security challenges of large AI models. A balanced approach to performance and security is essential for developing reliable deep learning systems.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 22 of its 84 references that are in the map. First posted on arXiv 12 Dec 2024.

Builds on

22 of 84 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Poisoning Attacks and Defenses on Artificial Intelligence: A Survey21 Feb

Other references · 21

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  6. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  7. 2017Adversarial Attacks on Neural Network Policiescited by 314
  8. 2020Dynamical Variational Autoencoders: A Comprehensive Reviewcited by 127
  9. 2015Adversarial Manipulation of Deep Representationscited by 56
  10. 2018Deep Learning using Rectified Linear Units (ReLU)cited by 43
  11. 2017Adversarial Examples that Fool Detectorscited by 39
  12. 2020Defending Model Inversion and Membership Inference Attacks via Prediction Purificationcited by 32
9 more
  1. 2018Logit Pairing Methods Can Fool Gradient-Based Attackscited by 27
  2. 2023Automated Cyber Defence: A Reviewcited by 19
  3. 2021Fast Gradient Non-sign Methodscited by 9
  4. 2023High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackerscited by 7
  5. 2022A Survey on Poisoning Attacks Against Supervised Machine Learningcited by 5
  6. 2015A Review of Network Traffic Analysis and Prediction Techniquescited by 4
  7. 2024Deep Learning and Machine Learning -- Object Detection and Semantic Segmentation: From Theory to Applicationscited by 2
  8. 2024Deep Learning, Machine Learning -- Digital Signal and Image Processing: From Theory to Applicationcited by 2
  9. 2024Deep Learning and Machine Learning -- Python Data Structures and Mathematics Fundamental: From Theory to Practicecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applicationscited by 40
  2. 2026A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctionscited by 0
  3. 2026FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Driftcited by 0
  4. 2026On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Modelscited by 0