REVIEW 6 cited by
Towards Adversarial Evaluations for Inexact Machine Unlearning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of affected training data from a learned model. Achieving this task exactly is computationally expensive; consequently, recent works have proposed inexact unlearning algorithms to solve this approximately as well as evaluation methods to test the effectiveness of these algorithms. In this work, we first outline some necessary criteria for evaluation methods and show no existing evaluation satisfies them all. Then, we design a stronger black-box evaluation method called the Interclass Confusion (IC) test which adversarially manipulates data during training to detect the insufficiency of unlearning procedures. We also propose two analytically motivated baseline methods~(EU-k and CF-k) which outperform several popular inexact unlearning methods. Overall, we demonstrate how adversarial evaluation strategies can help in analyzing various unlearning phenomena which can guide the development of stronger unlearning algorithms.
Forward citations
Cited by 6 Pith papers
-
The Space Complexity of Learning-Unlearning Algorithms
The space complexity of machine unlearning for realizability testing is characterized by eluder dimension (central lower bound), star number (ticketed upper bound), and hollow star number (bounded deletions), separati...
-
System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
The paper introduces system-aware unlearning and gives the first exact unlearning algorithm for linear classification that stores a sublinear-size core set instead of the entire dataset.
-
Leveraging Per-Instance Privacy for Machine Unlearning
Per-instance privacy losses, estimated from gradient norms during training, predict the number of fine-tuning steps needed for machine unlearning and rank data points by unlearning difficulty.
-
Soft Weighted Machine Unlearning
Soft-weighted unlearning replaces binary data removal with per-sample weights from a convex quadratic program, improving fairness and robustness gains while preserving utility.
-
Superior resilience to poisoning and amenability to unlearning in quantum machine learning
A simulator study reports that QNNs hold accuracy under label flipping better than a large MLP and unlearn faster, but the claimed fundamental advantage is not established without regularized classical baselines.
-
Forget-MI: Machine Unlearning for Forgetting Multimodal Information in Healthcare Settings
Forget-MI unlearns unimodal and joint embeddings of patient data in a multimodal chest X-ray model, reducing membership inference attack success by 0.202 while preserving only part of the original test performance.
Discussion (0). Sign in to comment.