# Deep Learning Model Security: Threats and Defenses

arXiv: https://arxiv.org/abs/2412.08969 · HTML: https://mlsanity.com/paper/2412.08969/

## Key facts

- Cited by 4 papers in the map (data through 14 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.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 22 of 22)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Dynamical Variational Autoencoders: A Comprehensive Review](https://mlsanity.com/paper/2008.12595/) (2020)
- [Adversarial Manipulation of Deep Representations](https://mlsanity.com/paper/1511.05122/) (2015)
- [Deep Learning using Rectified Linear Units (ReLU)](https://mlsanity.com/paper/1803.08375/) (2018)
- [Adversarial Examples that Fool Detectors](https://mlsanity.com/paper/1712.02494/) (2017)
- [Defending Model Inversion and Membership Inference Attacks via Prediction Purification](https://mlsanity.com/paper/2005.03915/) (2020)
- [Logit Pairing Methods Can Fool Gradient-Based Attacks](https://mlsanity.com/paper/1810.12042/) (2018)
- [Automated Cyber Defence: A Review](https://mlsanity.com/paper/2303.04926/) (2023)
- [Poisoning Attacks and Defenses on Artificial Intelligence: A Survey](https://mlsanity.com/paper/2202.10276/) (2022)
- [Fast Gradient Non-sign Methods](https://mlsanity.com/paper/2110.12734/) (2021)
- [High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers](https://mlsanity.com/paper/2307.13352/) (2023)
- [A Survey on Poisoning Attacks Against Supervised Machine Learning](https://mlsanity.com/paper/2202.02510/) (2022)
- [A Review of Network Traffic Analysis and Prediction Techniques](https://mlsanity.com/paper/1507.05722/) (2015)
- [Deep Learning and Machine Learning -- Object Detection and Semantic Segmentation: From Theory to Applications](https://mlsanity.com/paper/2410.15584/) (2024)
- [Deep Learning, Machine Learning -- Digital Signal and Image Processing: From Theory to Application](https://mlsanity.com/paper/2410.20304/) (2024)
- [Deep Learning and Machine Learning -- Python Data Structures and Mathematics Fundamental: From Theory to Practice](https://mlsanity.com/paper/2410.19849/) (2024)

## Built on by (most cited first, 4 of 4)

- [A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications](https://mlsanity.com/paper/2503.17003/) (2025)
- [A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctions](https://mlsanity.com/paper/2606.28943/) (2026)
- [FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift](https://mlsanity.com/paper/2607.09695/) (2026)
- [On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models](https://mlsanity.com/paper/2608.10530/) (2026)

## 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.