Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective

• URL: http://arxiv.org/abs/2506.13009v1
• Date: Mon, 16 Jun 2025 00:30:02 GMT
• Title: Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
• Authors: Nima Naderloui, Shenao Yan, Binghui Wang, Jie Fu, Wendy Hui Wang, Weiran Liu, Yuan Hong,
• Abstract summary: We propose RULI (Rectified Unlearning Evaluation Framework via Likelihood Inference) to address critical gaps in the evaluation of inexact unlearning methods.<n>RULI introduces a dual-objective attack to measure both unlearning efficacy and privacy risks at a per-sample granularity.<n>Our findings reveal significant vulnerabilities in state-of-the-art unlearning methods, exposing privacy risks underestimated by existing methods.
• Score: 42.003102851493885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning ensures complete data removal equivalent to retraining, it is impractical for large-scale models, leading to growing interest in inexact unlearning methods. However, the lack of formal guarantees in these methods necessitates the need for robust evaluation frameworks to assess their privacy and effectiveness. In this work, we first identify several key pitfalls of the existing unlearning evaluation frameworks, e.g., focusing on average-case evaluation or targeting random samples for evaluation, incomplete comparisons with the retraining baseline. Then, we propose RULI (Rectified Unlearning Evaluation Framework via Likelihood Inference), a novel framework to address critical gaps in the evaluation of inexact unlearning methods. RULI introduces a dual-objective attack to measure both unlearning efficacy and privacy risks at a per-sample granularity. Our findings reveal significant vulnerabilities in state-of-the-art unlearning methods, where RULI achieves higher attack success rates, exposing privacy risks underestimated by existing methods. Built on a game-based foundation and validated through empirical evaluations on both image and text data (spanning tasks from classification to generation), RULI provides a rigorous, scalable, and fine-grained methodology for evaluating unlearning techniques.

Related papers

• OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics [101.78963920333342]
  We introduce OpenUnlearning, a standardized framework for benchmarking large language models (LLMs) unlearning methods and metrics.<n>OpenUnlearning integrates 9 unlearning algorithms and 16 diverse evaluations across 3 leading benchmarks.<n>We also benchmark diverse unlearning methods and provide a comparative analysis against an extensive evaluation suite.
  arXiv  Detail & Related papers  (2025-06-14T20:16:37Z)
• MUBox: A Critical Evaluation Framework of Deep Machine Unlearning [13.186439491394474]
  MUBox is a comprehensive platform designed to evaluate unlearning methods in deep learning.<n> MUBox integrates 23 advanced unlearning techniques, tested across six practical scenarios with 11 diverse evaluation metrics.
  arXiv  Detail & Related papers  (2025-05-13T13:50:51Z)
• Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset [92.99416966226724]
  We introduce Facial Identity Unlearning Benchmark (FIUBench), a novel VLM unlearning benchmark designed to robustly evaluate the effectiveness of unlearning algorithms.<n>We apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels.<n>Through the evaluation of four baseline VLM unlearning algorithms within FIUBench, we find that all methods remain limited in their unlearning performance.
  arXiv  Detail & Related papers  (2024-11-05T23:26:10Z)
• FEDLAD: Federated Evaluation of Deep Leakage Attacks and Defenses [50.921333548391345]
  Federated Learning is a privacy preserving decentralized machine learning paradigm.<n>Recent research has revealed that private ground truth data can be recovered through a gradient technique known as Deep Leakage.<n>This paper introduces the FEDLAD Framework (Federated Evaluation of Deep Leakage Attacks and Defenses), a comprehensive benchmark for evaluating Deep Leakage attacks and defenses.
  arXiv  Detail & Related papers  (2024-11-05T11:42:26Z)
• A practical approach to evaluating the adversarial distance for machine learning classifiers [2.2120851074630177]
  This paper investigates the estimation of the more informative adversarial distance using iterative adversarial attacks and a certification approach. We find that our adversarial attack approach is effective compared to related implementations, while the certification method falls short of expectations.
  arXiv  Detail & Related papers  (2024-09-05T14:57:01Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Towards Reliable Empirical Machine Unlearning Evaluation: A Cryptographic Game Perspective [5.724350004671127]
  Machine unlearning updates machine learning models to remove information from specific training samples, complying with data protection regulations.<n>Despite the recent development of numerous unlearning algorithms, reliable evaluation of these algorithms remains an open research question.<n>This work presents a novel and reliable approach to empirically evaluating unlearning algorithms, paving the way for the development of more effective unlearning techniques.
  arXiv  Detail & Related papers  (2024-04-17T17:20:27Z)
• A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification [0.491574468325115]
  We present a large-scale empirical study for the first time enabling benchmarking confidence scoring functions. The revelation of a simple softmax response baseline as the overall best performing method underlines the drastic shortcomings of current evaluation.
  arXiv  Detail & Related papers  (2022-11-28T12:25:27Z)
• Evaluating Machine Unlearning via Epistemic Uncertainty [78.27542864367821]
  This work presents an evaluation of Machine Unlearning algorithms based on uncertainty. This is the first definition of a general evaluation of our best knowledge.
  arXiv  Detail & Related papers  (2022-08-23T09:37:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.