ORCID

Abstract

Enforcing the Right-to-be-Forgotten (RtBF) in transformer models remains challenging: full retraining is costly, while post-hoc unlearning often leaves residual signal without guarantees. We propose an RtBF-by-design protocol for adapter-tuned models that combines differential privacy (DP) applied to Low-Rank Adaptation (LoRA) adapters with a matched-control Deletion Sufficiency Certificate (DSC). A DP-trained model on the full dataset is evaluated against an identically configured and trained redacted-control model using three complementary criteria - prediction agreement, membership-inference separability, and calibrated confidence exposure - to assess deletion sufficiency. The DSC offers an operational go/no-go decision for RtBF without requiring full retraining. Experiments on a text classification task show that multiple privacy budgets (e.g., e {5, 6, 8}) preserve near-baseline utility while meeting all deletion sufficiency criteria, whereas post-hoc unlearning baselines either degrade utility or exhibit strong residual leakage. The protocol provides a lightweight, reproducible pathway to RtBF compliance in adapter-based fine-tuning.

Keywords

Differential Privacy, HCAI, Machine Unlearning, Parameter-Efficient Fine-Tuning (PEFT), Right-to-be-Forgotten (RtBF)

Publication Date

2026-02-16

Event

3rd International Conference on Human-Centred AI - Education and Practice, HCAI-ep 2026

Publication Title

HCAI-ep 2026 - Proceedings of the 2026 Conference on Human Centered Artificial Intelligence - Education and Practice

Publisher

Association for Computing Machinery (ACM)

ISBN

9798400721533

First Page

93

Last Page

99

Deposit Date

2026-05-12

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download


Share

COinS