arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07919cs.AIcs.CV
收藏

针对目标和鲁棒概念反学习的精选微调

Selective Fine-Tuning for Targeted and Robust Concept Unlearning

Department of Computing(计算系)

Mansi, Avinash Kori, Francesca Toni, Soteris Demetriou

AI总结:

TRUST通过动态估计目标概念神经元并结合Hessian正则化,实现高效且鲁棒的概念反学习,同时保持生成质量并提升效率。

摘要:

文本引导的扩散模型被数百万用户使用,但容易被利用来生成有害内容。概念反学习方法旨在减少模型生成有害内容的可能性。传统上,这在个体概念层面进行处理,只有少数近期工作考虑了更现实的概念组合。然而,最先进的方法依赖于完整的微调,这在计算上是昂贵的。概念定位方法可以促进选择性微调,但现有技术是静态的,导致效用不足。为了应对这些挑战,我们提出了TRUST(目标鲁棒选择性微调),一种新的方法,通过Hessian基于的正则化,动态估计目标概念神经元并通过选择性微调进行反学习。我们通过实验表明,与多个SOTA基线相比,TRUST在对抗性提示下具有鲁棒性,生成质量得到显著保留,并且比SOTA快得多。我们的方法实现了对单个概念以及概念组合和条件概念的反学习,而无需任何特定的正则化。

英文摘要:

Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has been tackled at an individual concept level, with only a handful of recent works considering more realistic concept combinations. However, state of the art methods depend on full finetuning, which is computationally expensive. Concept localisation methods can facilitate selective finetuning, but existing techniques are static, resulting in suboptimal utility. In order to tackle these challenges, we propose TRUST (Targeted Robust Selective fine Tuning), a novel approach for dynamically estimating target concept neurons and unlearning them through selective finetuning, empowered by a Hessian based regularization. We show experimentally, against a number of SOTA baselines, that TRUST is robust against adversarial prompts, preserves generation quality to a significant degree, and is also significantly faster than the SOTA. Our method achieves unlearning of not only individual concepts but also combinations of concepts and conditional concepts, without any specific regularization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑