# Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation

arXiv: https://arxiv.org/abs/2410.23693 · HTML: https://mlsanity.com/paper/2410.23693/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 28 of its 50 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [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)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening](https://mlsanity.com/paper/2308.07707/) (2023)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Boundary Unlearning](https://mlsanity.com/paper/2303.11570/) (2023)
- [Zero-Shot Machine Unlearning](https://mlsanity.com/paper/2201.05629/) (2022)
- [Learning how to explain neural networks: PatternNet and PatternAttribution](https://mlsanity.com/paper/1705.05598/) (2017)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [Learn to Forget: Machine Unlearning via Neuron Masking](https://mlsanity.com/paper/2003.10933/) (2020)
- [The Lottery Ticket Hypothesis for Object Recognition](https://mlsanity.com/paper/2012.04643/) (2020)
- [Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systems](https://mlsanity.com/paper/2311.02240/) (2023)
- [Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization](https://mlsanity.com/paper/2202.00232/) (2022)
- [Targeted Unlearning with Single Layer Unlearning Gradient](https://mlsanity.com/paper/2407.11867/) (2024)
- [Novel Class Discovery for Ultra-Fine-Grained Visual Categorization](https://mlsanity.com/paper/2405.06283/) (2024)
- [Generative Adversarial Networks Unlearning](https://mlsanity.com/paper/2308.09881/) (2023)
- [Don't Forget Too Much: Towards Machine Unlearning on Feature Level](https://mlsanity.com/paper/2406.10951/) (2024)
- [Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers](https://mlsanity.com/paper/2408.12568/) (2024)
- [Random Relabeling for Efficient Machine Unlearning](https://mlsanity.com/paper/2305.12320/) (2023)
- [Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning](https://mlsanity.com/paper/2405.15662/) (2024)
- [Towards Efficient Target-Level Machine Unlearning Based on Essential Graph](https://mlsanity.com/paper/2406.10954/) (2024)

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

- [On the Necessity of Output Distribution Reweighting for Effective Class Unlearning](https://mlsanity.com/paper/2506.20893/) (2025)
- [From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models](https://mlsanity.com/paper/2506.21609/) (2025)
- [Unmerge: Efficient Machine Unlearning via Task Arithmetic](https://mlsanity.com/paper/2609.38895/) (2026)
- [UnAct: Gradient-Free Unlearning via Targeted Activation Intervention](https://mlsanity.com/paper/2610.04426/) (2026)

## Abstract (arXiv)

In the rapid advancement of artificial intelligence, privacy protection has become crucial, giving rise to machine unlearning. Machine unlearning is a technique that removes specific data influences from trained models without the need for extensive retraining. However, it faces several key challenges, including accurately implementing unlearning, ensuring privacy protection during the unlearning process, and achieving effective unlearning without significantly compromising model performance. This paper presents a novel approach to machine unlearning by employing Layer-wise Relevance Analysis and Neuronal Path Perturbation. We address three primary challenges: the lack of detailed unlearning principles, privacy guarantees in zero-shot unlearning scenario, and the balance between unlearning effectiveness and model utility. Our method balances machine unlearning performance and model utility by identifying and perturbing highly relevant neurons, thereby achieving effective unlearning. By using data not present in the original training set during the unlearning process, we satisfy the zero-shot unlearning scenario and ensure robust privacy protection. Experimental results demonstrate that our approach effectively removes targeted data from the target unlearning model while maintaining the model's utility, offering a practical solution for privacy-preserving machine learning.