SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders

Enrico Cassano, Riccardo Renzulli, Marco Nurisso, Mirko Zaffaroni, Alan Perotti, Marco Grangetto
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:12001-12023, 2026.

Abstract

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse autoencoder framework that overcomes this by enforcing one-to-one concept-neuron mappings. By systematically labeling concepts during training, our method achieves feature centralization, binding each concept to a single, interpretable neuron. This enables highly targeted and efficient concept erasure. Compared to the state-of-the-art sparse autoencoder-based unlearning approach, SAEmnesia reduces hyperparameter search by 96.67% and achieves a 9.22% improvement on the UnlearnCanvas benchmark for objects. Our method also shows superior scalability in sequential unlearning, improving accuracy by 28.4% when removing nine objects, establishing a step forward for precise and controllable concept erasure. Moreover, SAEmnesia effectively suppresses nudity on the I2P benchmark and remains robust to adversarial attacks. Source code available at https://github.com/EIDOSLAB/SAEmnesia.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-cassano26a, title = {{SAE}mnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders}, author = {Cassano, Enrico and Renzulli, Riccardo and Nurisso, Marco and Zaffaroni, Mirko and Perotti, Alan and Grangetto, Marco}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {12001--12023}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/cassano26a/cassano26a.pdf}, url = {https://proceedings.mlr.press/v306/cassano26a.html}, abstract = {Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse autoencoder framework that overcomes this by enforcing one-to-one concept-neuron mappings. By systematically labeling concepts during training, our method achieves feature centralization, binding each concept to a single, interpretable neuron. This enables highly targeted and efficient concept erasure. Compared to the state-of-the-art sparse autoencoder-based unlearning approach, SAEmnesia reduces hyperparameter search by 96.67% and achieves a 9.22% improvement on the UnlearnCanvas benchmark for objects. Our method also shows superior scalability in sequential unlearning, improving accuracy by 28.4% when removing nine objects, establishing a step forward for precise and controllable concept erasure. Moreover, SAEmnesia effectively suppresses nudity on the I2P benchmark and remains robust to adversarial attacks. Source code available at https://github.com/EIDOSLAB/SAEmnesia.} }
Endnote
%0 Conference Paper %T SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders %A Enrico Cassano %A Riccardo Renzulli %A Marco Nurisso %A Mirko Zaffaroni %A Alan Perotti %A Marco Grangetto %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-cassano26a %I PMLR %P 12001--12023 %U https://proceedings.mlr.press/v306/cassano26a.html %V 306 %X Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse autoencoder framework that overcomes this by enforcing one-to-one concept-neuron mappings. By systematically labeling concepts during training, our method achieves feature centralization, binding each concept to a single, interpretable neuron. This enables highly targeted and efficient concept erasure. Compared to the state-of-the-art sparse autoencoder-based unlearning approach, SAEmnesia reduces hyperparameter search by 96.67% and achieves a 9.22% improvement on the UnlearnCanvas benchmark for objects. Our method also shows superior scalability in sequential unlearning, improving accuracy by 28.4% when removing nine objects, establishing a step forward for precise and controllable concept erasure. Moreover, SAEmnesia effectively suppresses nudity on the I2P benchmark and remains robust to adversarial attacks. Source code available at https://github.com/EIDOSLAB/SAEmnesia.
APA
Cassano, E., Renzulli, R., Nurisso, M., Zaffaroni, M., Perotti, A. & Grangetto, M.. (2026). SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:12001-12023 Available from https://proceedings.mlr.press/v306/cassano26a.html.

Related Material