# Zero-Shot Class Unlearning in CLIP with Synthetic Samples

arXiv: https://arxiv.org/abs/2407.07485 · HTML: https://mlsanity.com/paper/2407.07485/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Fast Yet Effective Machine Unlearning](https://mlsanity.com/paper/2111.08947/) (2021)
- [Spectral Norm Regularization for Improving the Generalizability of Deep Learning](https://mlsanity.com/paper/1705.10941/) (2017)
- [Zero-Shot Machine Unlearning](https://mlsanity.com/paper/2201.05629/) (2022)
- [Machine Unlearning: A Survey](https://mlsanity.com/paper/2306.03558/) (2023)

## Built on by (most cited first, 17 of 17)

- [MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2502.11051/) (2025)
- [CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP](https://mlsanity.com/paper/2410.23330/) (2024)
- [ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.20358/) (2026)
- [Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks](https://mlsanity.com/paper/2607.07907/) (2026)
- [POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse](https://mlsanity.com/paper/2511.19339/) (2025)
- [Unlearning Personal Data from a Single Image](https://mlsanity.com/paper/2407.12069/) (2024)
- [Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting](https://mlsanity.com/paper/2507.20834/) (2025)
- [SineProject: Machine Unlearning for Stable Vision Language Alignment](https://mlsanity.com/paper/2511.18444/) (2025)
- [SALMUBench: A Benchmark for Sensitive Association-Level Multimodal Unlearning](https://mlsanity.com/paper/2603.26316/) (2026)
- [Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach](https://mlsanity.com/paper/2512.14113/) (2025)
- [CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic](https://mlsanity.com/paper/2605.18610/) (2026)
- [Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU](https://mlsanity.com/paper/2503.15166/) (2025)
- [Unlearning the Noisy Correspondence Makes CLIP More Robust](https://mlsanity.com/paper/2507.03434/) (2025)
- [Face Identity Unlearning for Retrieval via Embedding Dispersion](https://mlsanity.com/paper/2512.13317/) (2025)
- [Erasing CLIP Memories: Non-Destructive, Data-Free Zero-Shot class Unlearning in CLIP Models](https://mlsanity.com/paper/2512.14137/) (2025)
- [ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition](https://mlsanity.com/paper/2605.14309/) (2026)
- [Damnatio Memoriae: Adversarially and Selectively Forgetting Identities in the Embedding Space of Face Recognition Models](https://mlsanity.com/paper/2609.27115/) (2026)

## Abstract (arXiv)

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.