# Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses

arXiv: https://arxiv.org/abs/2012.10544 · HTML: https://mlsanity.com/paper/2012.10544/

## Key facts

- Cited by 180 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2020.

## Built on by (most cited first, 30 of 180)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Boundary Unlearning](https://mlsanity.com/paper/2303.11570/) (2023)
- [Adversarial Examples Make Strong Poisons](https://mlsanity.com/paper/2106.10807/) (2021)
- [Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning](https://mlsanity.com/paper/2108.10241/) (2021)
- [Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch](https://mlsanity.com/paper/2106.08970/) (2021)
- [Neurotoxin: Durable Backdoors in Federated Learning](https://mlsanity.com/paper/2206.10341/) (2022)
- [Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning](https://mlsanity.com/paper/2205.01992/) (2022)
- [Diffusion Models for Imperceptible and Transferable Adversarial Attack](https://mlsanity.com/paper/2305.08192/) (2023)
- [BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models](https://mlsanity.com/paper/2110.02467/) (2021)
- [BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models](https://mlsanity.com/paper/2401.12242/) (2024)
- [Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models](https://mlsanity.com/paper/2310.13828/) (2023)
- [Unleashing the potential of prompt engineering for large language models](https://mlsanity.com/paper/2310.14735/) (2023)
- [Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents](https://mlsanity.com/paper/2411.09523/) (2024)
- [Availability Attacks Create Shortcuts](https://mlsanity.com/paper/2111.00898/) (2021)
- [Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training](https://mlsanity.com/paper/2102.04716/) (2021)
- [Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation](https://mlsanity.com/paper/2202.02628/) (2022)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks](https://mlsanity.com/paper/2502.08586/) (2025)
- [An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry](https://mlsanity.com/paper/2303.02552/) (2023)
- [Autoregressive Perturbations for Data Poisoning](https://mlsanity.com/paper/2206.03693/) (2022)
- [Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks](https://mlsanity.com/paper/2212.10717/) (2022)
- [Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.10701/) (2023)
- [Machine Unlearning Fails to Remove Data Poisoning Attacks](https://mlsanity.com/paper/2406.17216/) (2024)
- [Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release](https://mlsanity.com/paper/2103.02683/) (2021)
- [DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations](https://mlsanity.com/paper/2103.02079/) (2021)
- [Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions](https://mlsanity.com/paper/2303.02213/) (2023)
- [Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks](https://mlsanity.com/paper/2308.04451/) (2023)
- [Don't trust your eyes: on the (un)reliability of feature visualizations](https://mlsanity.com/paper/2306.04719/) (2023)
- [Towards Stable Backdoor Purification through Feature Shift Tuning](https://mlsanity.com/paper/2310.01875/) (2023)
- [Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound](https://mlsanity.com/paper/2307.08208/) (2023)

## Abstract (arXiv)

As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy human supervision over the data collection process exposes organizations to security vulnerabilities; training data can be manipulated to control and degrade the downstream behaviors of learned models. The goal of this work is to systematically categorize and discuss a wide range of dataset vulnerabilities and exploits, approaches for defending against these threats, and an array of open problems in this space. In addition to describing various poisoning and backdoor threat models and the relationships among them, we develop their unified taxonomy.