mlsanityData to 7 Oct 2026

TruVRF: Towards Triple-Granularity Verification on Machine Unlearning

arXiv 2408.06063 ↗First posted 12 Aug 2024cs.LG cs.CRcited by 4

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

The concept of the right to be forgotten has led to growing interest in machine unlearning, but reliable validation methods are lacking, creating opportunities for dishonest model providers to mislead data contributors. Traditional invasive methods like backdoor injection are not feasible for legacy data. To address this, we introduce TruVRF, a non-invasive unlearning verification framework operating at class-, volume-, and sample-level granularities. TruVRF includes three Unlearning-Metrics designed to detect different types of dishonest servers: Neglecting, Lazy, and Deceiving. Unlearning-Metric-I checks class alignment, Unlearning-Metric-II verifies sample count, and Unlearning-Metric-III confirms specific sample deletion. Evaluations on three datasets show TruVRF's robust performance, with over 90% accuracy for Metrics I and III, and a 4.8% to 8.2% inference deviation for Metric II. TruVRF also demonstrates generalizability and practicality across various conditions and with state-of-the-art unlearning frameworks like SISA and Amnesiac Unlearning.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 14 of its 50 references that are in the map. First posted on arXiv 12 Aug 2024.

Builds on

14 of 50 references.

Closest ancestors · 3

Same direction, newest first

  1. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning22 Oct
  2. 2021Adaptive Machine Unlearning8 Jun
  3. 2021Remember What You Want to Forget: Algorithms for Machine Unlearning4 Mar

Other references · 11

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2019Certified Data Removal from Machine Learning Modelscited by 512
  3. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  4. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  5. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  6. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 258
  7. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  8. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 143
  9. 2020Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Reviewcited by 120
  10. 2021Manipulating SGD with Data Ordering Attackscited by 73
  11. 2022Training with More Confidence: Mitigating Injected and Natural Backdoors During Trainingcited by 38

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Towards Reliable Forgetting: A Survey on Machine Unlearning Verificationcited by 8
  2. 2025External Data Extraction Attacks against Retrieval-Augmented Large Language Modelscited by 2
  3. 2025ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofscited by 1
  4. 2026Governing AI Forgetting: Auditing for Machine Unlearning Compliancecited by 1