# Security and Privacy Issues in Deep Learning

arXiv: https://arxiv.org/abs/1807.11655 · HTML: https://mlsanity.com/paper/1807.11655/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2018.

## Built on by (most cited first, 19 of 19)

- [Continual Learning and Private Unlearning](https://mlsanity.com/paper/2203.12817/) (2022)
- [Security and Privacy for Artificial Intelligence: Opportunities and Challenges](https://mlsanity.com/paper/2102.04661/) (2021)
- [Establishing and Evaluating Trustworthy AI: Overview and Research Challenges](https://mlsanity.com/paper/2411.09973/) (2024)
- [Beyond Mahalanobis-Based Scores for Textual OOD Detection](https://mlsanity.com/paper/2211.13527/) (2022)
- [Review on the Feasibility of Adversarial Evasion Attacks and Defenses for Network Intrusion Detection Systems](https://mlsanity.com/paper/2303.07003/) (2023)
- [Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review](https://mlsanity.com/paper/2306.00687/) (2023)
- [Testing Feedforward Neural Networks Training Programs](https://mlsanity.com/paper/2204.00694/) (2022)
- [Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2502.16708/) (2025)
- [VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference](https://mlsanity.com/paper/2509.24257/) (2025)
- [Security and Privacy Challenges in Deep Learning Models](https://mlsanity.com/paper/2311.13744/) (2023)
- [Towards Transparency: Exploring LLM Trainings Datasets through Visual Topic Modeling and Semantic Frame](https://mlsanity.com/paper/2406.06574/) (2024)
- [Random Sampling for Diffusion-based Adversarial Purification](https://mlsanity.com/paper/2411.18956/) (2024)
- [PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion](https://mlsanity.com/paper/2509.16897/) (2025)
- [Unlearning in Diffusion models under Data Constraints: A Variational Inference Approach](https://mlsanity.com/paper/2510.04058/) (2025)
- [Adopting Two Supervisors for Efficient Use of Large-Scale Remote Deep Neural Networks](https://mlsanity.com/paper/2304.02654/) (2023)
- [Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models](https://mlsanity.com/paper/2309.13579/) (2023)
- [Mobile Application for Oral Disease Detection using Federated Learning](https://mlsanity.com/paper/2403.12044/) (2023)
- [Deep Learning Under Siege: Identifying Security Vulnerabilities and Risk Mitigation Strategies](https://mlsanity.com/paper/2409.09517/) (2024)
- [Artificial Intelligence and Innovation Ecosystem: Evolutionary Developments, Challenges, and Future Directions](https://mlsanity.com/paper/2607.24589/) (2026)

## Abstract (arXiv)

To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that can compromise its integrity and efficiency. Security attacks can be divided based on when they occur: if an attack occurs during training, it is known as a poisoning attack, and if it occurs during inference (after training) it is termed an evasion attack. Poisoning attacks compromise the training process by corrupting the data with malicious examples, while evasion attacks use adversarial examples to disrupt entire classification process. Defenses proposed against such attacks include techniques to recognize and remove malicious data, train a model to be insensitive to such data, and mask the model's structure and parameters to render attacks more challenging to implement. Furthermore, the privacy of the data involved in model training is also threatened by attacks such as the model-inversion attack, or by dishonest service providers of AI applications. To maintain data privacy, several solutions that combine existing data-privacy techniques have been proposed, including differential privacy and modern cryptography techniques. In this paper, we describe the notions of some of methods, e.g., homomorphic encryption, and review their advantages and challenges when implemented in deep-learning models.