# Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning

arXiv: https://arxiv.org/abs/2404.03233 · HTML: https://mlsanity.com/paper/2404.03233/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 44 of its 65 references that are in the map.
- First posted on arXiv 4 Apr 2024.

## Placed in

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

## Builds on (most cited first, 30 of 44)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Label-Only Membership Inference Attacks](https://mlsanity.com/paper/2007.14321/) (2020)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning](https://mlsanity.com/paper/1812.00535/) (2018)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)

## Built on by (most cited first, 30 of 48)

- [Machine Unlearning: A Comprehensive Survey](https://mlsanity.com/paper/2405.07406/) (2024)
- [Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable](https://mlsanity.com/paper/2405.20272/) (2024)
- [Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security](https://mlsanity.com/paper/2404.05264/) (2024)
- [Depth Gives a False Sense of Privacy: LLM Internal States Inversion](https://mlsanity.com/paper/2507.16372/) (2025)
- [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)
- [Textual Unlearning Gives a False Sense of Unlearning](https://mlsanity.com/paper/2406.13348/) (2024)
- [Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices](https://mlsanity.com/paper/2410.10128/) (2024)
- [Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning](https://mlsanity.com/paper/2501.16663/) (2025)
- [Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective](https://mlsanity.com/paper/2506.13009/) (2025)
- [Towards Reliable Forgetting: A Survey on Machine Unlearning Verification](https://mlsanity.com/paper/2506.15115/) (2025)
- [TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning](https://mlsanity.com/paper/2502.19770/) (2025)
- [Privacy-Preserving Federated Unlearning with Certified Client Removal](https://mlsanity.com/paper/2404.09724/) (2024)
- [Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM](https://mlsanity.com/paper/2505.24379/) (2025)
- [Exposing Privacy Risks in Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.17222/) (2025)
- [How Secure is Forgetting? Linking Machine Unlearning to Machine Learning Attacks](https://mlsanity.com/paper/2503.20257/) (2025)
- [Unlearning Inversion Attacks for Graph Neural Networks](https://mlsanity.com/paper/2506.00808/) (2025)
- [Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack](https://mlsanity.com/paper/2506.01318/) (2025)
- [Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy](https://mlsanity.com/paper/2507.20573/) (2025)
- [Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods](https://mlsanity.com/paper/2508.12730/) (2025)
- [Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models](https://mlsanity.com/paper/2512.18035/) (2025)
- [ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation](https://mlsanity.com/paper/2412.21123/) (2024)
- [CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning](https://mlsanity.com/paper/2503.00062/) (2025)
- [Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses](https://mlsanity.com/paper/2508.19641/) (2025)
- [Model Inversion Attack against Federated Unlearning](https://mlsanity.com/paper/2502.14558/) (2025)
- [One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting](https://mlsanity.com/paper/2507.07754/) (2025)
- [AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs](https://mlsanity.com/paper/2505.11557/) (2025)
- [Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy](https://mlsanity.com/paper/2506.19486/) (2025)
- [BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning](https://mlsanity.com/paper/2508.15541/) (2025)
- [SMS: Self-supervised Model Seeding for Verification of Machine Unlearning](https://mlsanity.com/paper/2509.25613/) (2025)

## Abstract (arXiv)

Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning mainly focus on the efficacy and efficiency of unlearning methods, while neglecting the investigation of the privacy vulnerability during the unlearning process. With two versions of a model available to an adversary, that is, the original model and the unlearned model, machine unlearning opens up a new attack surface. In this paper, we conduct the first investigation to understand the extent to which machine unlearning can leak the confidential content of the unlearned data. Specifically, under the Machine Learning as a Service setting, we propose unlearning inversion attacks that can reveal the feature and label information of an unlearned sample by only accessing the original and unlearned model. The effectiveness of the proposed unlearning inversion attacks is evaluated through extensive experiments on benchmark datasets across various model architectures and on both exact and approximate representative unlearning approaches. The experimental results indicate that the proposed attack can reveal the sensitive information of the unlearned data. As such, we identify three possible defenses that help to mitigate the proposed attacks, while at the cost of reducing the utility of the unlearned model. The study in this paper uncovers an underexplored gap between machine unlearning and the privacy of unlearned data, highlighting the need for the careful design of mechanisms for implementing unlearning without leaking the information of the unlearned data.