Metraipolis › archive › dc_62d0944703fa
PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders — arXiv:2608.10985
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10985
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:30:35.454Z
- SHA-256 of the archived text
4d3e077820ff572f0c1cb7172b96e4653d42ceee24338a204e753e403669426c- Stable URL of this page
https://metraipolis.com/documento/dc_62d0944703fa
How to cite
PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders — arXiv:2608.10985 — arXiv (en), https://arxiv.org/abs/2608.10985 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62d0944703fa (Metraipolis archive dc_62d0944703fa, sha256 4d3e077820ff572f0c1cb7172b96e4653d42ceee24338a204e753e403669426c)
BibTeX
@misc{dc62d0944703fa,
title = {PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders — arXiv:2608.10985},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10985},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62d0944703fa; sha256 4d3e077820ff572f0c1cb7172b96e4653d42ceee24338a204e753e403669426c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10985. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, privacy violations, and offensive content. Existing approaches struggle to achieve both precise and persistent concept erasure: inaccurate localization of concept-related representations may cause unintended semantic interference, while incomplete removal of the underlying concept knowledge allows adversarial recovery. To address this dilemma, we propose PEAK, a \textbf{\textit{precise}} and \textbf{\textit{persistent}} concept erasure framework via k-Sparse Autoencoders (kSAEs). PEAK first trains a kSAE on internal activations of the diffusion denoising network to decompose dense representations into interpretable sparse features. By contrasting sparse activations induced by target and non-target prompts, PEAK identifies a compact set of target-specific features according to both activation strength and frequency. These localized features are then used for parameter optimization, where PEAK selectively suppresses target-related activations while preserving complementary non-target ones towards the original model. This feature-guided optimization embeds concept erasure directly into diffusion parameters, eliminating the need for additional inference-time intervention and facilitating effective persistence against adversarial attacks. Extensive experiments demonstrate that PEAK achieves effective and robust concept erasure. On the I2P benchmark, PEAK reduces NudeNet detections from 582 to 6, lowers the average attack success rate (ASR) from 96.52\% to 5.63\%, and preserves general generation quality on MS-COCO with a near-zero KID. Our code and models are available at: this https URL
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.10985 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T06:25:27.306Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).