扩散模型中的记忆图像共享一个可定位和删除的子空间
Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted
AI总结：
本文发现扩散模型中的记忆现象集中在一个可定位的共享子空间，并提出一种通过修剪该子空间权重来缓解记忆、抵御数据提取攻击的事后模型编辑方法。
摘要：
大规模文本到图像扩散模型在根据文本输入生成高质量图像方面表现出色，但研究表明它们倾向于记忆并复制训练数据，引发了版权侵权和隐私问题。文本到图像社区为解决记忆问题所做的努力，探索了数据重复、标题复制或触发标记等成因，并提出了针对每个提示的推理时或训练时缓解策略。在本文中，我们聚焦于前馈层，首先对比了一组记忆和非记忆提示的神经元激活情况。实验揭示了一个令人惊讶的发现：许多不同的记忆提示集合显著激活了模型中的一个共同子空间，这首次证明了扩散模型中的记忆存在于一个特殊的子空间中。随后，我们引入一种新颖的事后编辑预训练模型的方法，通过直接修剪特定子空间中的权重来缓解记忆问题，避免了以往研究中需要干扰训练或推理过程的需求。最后，我们展示了修剪后的模型对训练数据提取攻击的鲁棒性，从而为解决记忆问题开辟了实用且通用的全新途径。
英文摘要：
Large-scale text-to-image diffusion models excel in generating high-quality images from textual inputs, yet concerns arise as research indicates their tendency to memorize and replicate training data, raising We also addressed the issue of memorization in diffusion models, where models tend to replicate exact training samples raising copyright infringement and privacy issues. Efforts within the text-to-image community to address memorization explore causes such as data duplication, replicated captions, or trigger tokens, proposing per-prompt inference-time or training-time mitigation strategies. In this paper, we focus on the feed-forward layers and begin by contrasting neuron activations of a set of memorized and non-memorized prompts. Experiments reveal a surprising finding: many different sets of memorized prompts significantly activate a common subspace in the model, demonstrating, for the first time, that memorization in the diffusion models lies in a special subspace. Subsequently, we introduce a novel post-hoc method for editing pre-trained models, whereby memorization is mitigated through the straightforward pruning of weights in specialized subspaces, avoiding the need to disrupt the training or inference process as seen in prior research. Finally, we demonstrate the robustness of the pruned model against training data extraction attacks, thereby unveiling new avenues for a practical and one-for-all solution to memorization.
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。
