# Hard to Forget: Poisoning Attacks on Certified Machine Unlearning

arXiv: https://arxiv.org/abs/2109.08266 · HTML: https://mlsanity.com/paper/2109.08266/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 33 of its 60 references that are in the map.
- First posted on arXiv 17 Sep 2021.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 33)

- [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)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Hidden Trigger Backdoor Attacks](https://mlsanity.com/paper/1910.00033/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [On Detecting Adversarial Perturbations](https://mlsanity.com/paper/1702.04267/) (2017)
- [A backdoor attack against LSTM-based text classification systems](https://mlsanity.com/paper/1905.12457/) (2019)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization](https://mlsanity.com/paper/1708.08689/) (2017)
- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations](https://mlsanity.com/paper/2003.02960/) (2020)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [Transferable Clean-Label Poisoning Attacks on Deep Neural Nets](https://mlsanity.com/paper/1905.05897/) (2019)
- [MetaPoison: Practical General-purpose Clean-label Data Poisoning](https://mlsanity.com/paper/2004.00225/) (2020)
- [Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks](https://mlsanity.com/paper/2006.12557/) (2020)
- [Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance](https://mlsanity.com/paper/1911.02466/) (2019)
- [A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference](https://mlsanity.com/paper/2010.02432/) (2020)
- [On the Suitability of Lp-norms for Creating and Preventing Adversarial Examples](https://mlsanity.com/paper/1802.09653/) (2018)
- [Algorithms that Remember: Model Inversion Attacks and Data Protection Law](https://mlsanity.com/paper/1807.04644/) (2018)
- [Towards Probabilistic Verification of Machine Unlearning](https://mlsanity.com/paper/2003.04247/) (2020)

## Built on by (most cited first, 30 of 52)

- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Fast Yet Effective Machine Unlearning](https://mlsanity.com/paper/2111.08947/) (2021)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [GIF: A General Graph Unlearning Strategy via Influence Function](https://mlsanity.com/paper/2304.02835/) (2023)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [Machine Unlearning in Generative AI: A Survey](https://mlsanity.com/paper/2407.20516/) (2024)
- [Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning](https://mlsanity.com/paper/2404.03233/) (2024)
- [Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks](https://mlsanity.com/paper/2212.10717/) (2022)
- [Algorithms that Approximate Data Removal: New Results and Limitations](https://mlsanity.com/paper/2209.12269/) (2022)
- [Threats, Attacks, and Defenses in Machine Unlearning: A Survey](https://mlsanity.com/paper/2403.13682/) (2024)
- [Machine Unlearning Fails to Remove Data Poisoning Attacks](https://mlsanity.com/paper/2406.17216/) (2024)
- [Machine Unlearning: A Comprehensive Survey](https://mlsanity.com/paper/2405.07406/) (2024)
- [A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services](https://mlsanity.com/paper/2309.08230/) (2023)
- [Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation](https://mlsanity.com/paper/2201.10055/) (2022)
- [Deep Regression Unlearning](https://mlsanity.com/paper/2210.08196/) (2022)
- [A Review on Machine Unlearning](https://mlsanity.com/paper/2411.11315/) (2024)
- [The Utility and Complexity of in- and out-of-Distribution Machine Unlearning](https://mlsanity.com/paper/2412.09119/) (2024)
- [Machine Unlearning: A Survey](https://mlsanity.com/paper/2306.03558/) (2023)
- [ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach](https://mlsanity.com/paper/2311.16136/) (2023)
- [A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks](https://mlsanity.com/paper/2406.06186/) (2024)
- [Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models](https://mlsanity.com/paper/2410.08074/) (2024)
- [BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap](https://mlsanity.com/paper/2506.15699/) (2025)
- [Exact Unlearning of Finetuning Data via Model Merging at Scale](https://mlsanity.com/paper/2504.04626/) (2025)
- [Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning](https://mlsanity.com/paper/2304.10638/) (2023)
- [DUCK: Distance-based Unlearning via Centroid Kinematics](https://mlsanity.com/paper/2312.02052/) (2023)
- [Uncovering Adversarial Risks of Test-Time Adaptation](https://mlsanity.com/paper/2301.12576/) (2023)
- [UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers](https://mlsanity.com/paper/2405.11336/) (2024)
- [Label Smoothing Improves Machine Unlearning](https://mlsanity.com/paper/2406.07698/) (2024)
- [Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning](https://mlsanity.com/paper/2501.16663/) (2025)
- [The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models](https://mlsanity.com/paper/2507.18725/) (2025)

## Abstract (arXiv)

The right to erasure requires removal of a user's information from data held by organizations, with rigorous interpretations extending to downstream products such as learned models. Retraining from scratch with the particular user's data omitted fully removes its influence on the resulting model, but comes with a high computational cost. Machine "unlearning" mitigates the cost incurred by full retraining: instead, models are updated incrementally, possibly only requiring retraining when approximation errors accumulate. Rapid progress has been made towards privacy guarantees on the indistinguishability of unlearned and retrained models, but current formalisms do not place practical bounds on computation. In this paper we demonstrate how an attacker can exploit this oversight, highlighting a novel attack surface introduced by machine unlearning. We consider an attacker aiming to increase the computational cost of data removal. We derive and empirically investigate a poisoning attack on certified machine unlearning where strategically designed training data triggers complete retraining when removed.