# PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning

arXiv: https://arxiv.org/abs/2604.22076 · HTML: https://mlsanity.com/paper/2604.22076/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Are Large Pre-Trained Language Models Leaking Your Personal Information?](https://mlsanity.com/paper/2205.12628/) (2022)
- [Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs](https://mlsanity.com/paper/2407.15549/) (2024)
- [Eight Methods to Evaluate Robust Unlearning in LLMs](https://mlsanity.com/paper/2402.16835/) (2024)
- [Catastrophic Failure of LLM Unlearning via Quantization](https://mlsanity.com/paper/2410.16454/) (2024)
- [Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond](https://mlsanity.com/paper/2502.05374/) (2025)
- [UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI](https://mlsanity.com/paper/2407.00106/) (2024)
- [Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities](https://mlsanity.com/paper/2502.05209/) (2025)
- [The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks](https://mlsanity.com/paper/2310.15469/) (2023)
- [Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness](https://mlsanity.com/paper/2506.05735/) (2025)

## Built on by (most cited first, 1 of 1)

- [K-Bench: A Benchmark for LLM Unlearning in Agentic Deployments](https://mlsanity.com/paper/2609.12808/) (2026)

## Abstract (arXiv)

Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its true effectiveness against privacy attacks remains unclear. To address this, we propose PrivUn, a new evaluation framework that systematically assesses unlearning robustness through three-tier attack scenarios: direct retrieval, in-context learning recovery, and fine-tuning restoration; combined with quantitative analysis using forgetting scores, association metrics, and forgetting depth assessment. Our study exposes significant weaknesses in current unlearning methods, revealing two key findings: 1) unlearning exhibits gradient-driven ripple effects: unlike traditional forgetting which follows semantic relations (e.g., knowledge graphs), privacy unlearning propagates across latent gradient-based associations; and 2) most methods suffer from shallow forgetting, failing to remove private information distributed across multiple deep model layers. To validate these insights, we explore two strategies: association-aware core-set selection that leverages gradient similarity, and multi-layer deep intervention through representational constraints. These strategies represent a paradigm shift from shallow forgetting to deep forgetting.