Papers › Zero-Shot Class Unlearning in CLIP with Synthetic Samples

Zero-Shot Class Unlearning in CLIP with Synthetic Samples

10 Jul 2024arXiv:2407.07485archive 2025-07-28

A. Kravets, V. Namboodiri

Machine unlearning is a crucial area of research. It is driven by the need to remove sensitive information from models to safeguard individuals' right to be forgotten under rigorous regulations such as GDPR. In this work, we focus on unlearning within CLIP, a dual vision-language encoder model trained on a massive dataset of image-text pairs using contrastive loss. To achieve forgetting we expand the application of Lipschitz regularization to the multimodal context of CLIP. Specifically, we ensure the smoothing of both visual and textual embeddings associated with the class intended to be forgotten relative to the perturbation introduced to the samples from that class. Additionally, importantly, we remove the necessity for real forgetting data by generating synthetic samples through gradient ascent maximizing the target class. Our forgetting procedure is iterative, where we track accuracy on a synthetic forget set and stop when accuracy falls below a chosen threshold. We employ a selective layers update strategy based on their average absolute gradient value to mitigate over-forgetting. We validate our approach on several standard datasets and provide thorough ablation analysis and comparisons with previous work.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

akres001/zero-shot-class-unlearning-in-clip-with-synthetic-samples officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Machine Unlearning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIPFocusSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections