扩散模型越强，后门越易：无需调整微调流程的数据投毒以诱发版权侵权
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline
AI总结：
本研究提出后门攻击方法SilentBadDiffusion，通过数据投毒诱发扩散模型版权侵权，无需控制训练流程，且模型越强攻击越易成功。
摘要：
文本到图像扩散模型（DMs）的商业化带来了潜在的版权问题。尽管已有众多尝试保护DMs免受版权问题困扰，但这些解决方案的脆弱性尚未得到充分探索。在本研究中，我们正式定义了针对生成式AI模型的版权侵权攻击，并提出了一种后门攻击方法SilentBadDiffusion，该方法无需访问或控制训练过程即可诱发版权侵权。我们的方法策略性地在投毒数据中嵌入版权信息与文本引用之间的连接，同时精心分散这些信息，使得投毒数据在融入干净数据集时不易被察觉。实验表明，投毒数据具有隐蔽性和有效性。当给定特定文本提示时，以0.20%的投毒比例训练的DMs能够生成受版权保护的图像。此外，结果还揭示，DMs越复杂，攻击越容易成功。这些发现凸显了现行版权保护策略中潜在缺陷，并强调了加强审查以防止DMs被滥用的必要性。
英文摘要：
The commercialization of text-to-image diffusion models (DMs) brings forth potential copyright concerns. Despite numerous attempts to protect DMs from copyright issues, the vulnerabilities of these solutions are underexplored. In this study, we formalized the Copyright Infringement Attack on generative AI models and proposed a backdoor attack method, SilentBadDiffusion, to induce copyright infringement without requiring access to or control over training processes. Our method strategically embeds connections between pieces of copyrighted information and text references in poisoning data while carefully dispersing that information, making the poisoning data inconspicuous when integrated into a clean dataset. Our experiments show the stealth and efficacy of the poisoning data. When given specific text prompts, DMs trained with a poisoning ratio of 0.20% can produce copyrighted images. Additionally, the results reveal that the more sophisticated the DMs are, the easier the success of the attack becomes. These findings underline potential pitfalls in the prevailing copyright protection strategies and underscore the necessity for increased scrutiny to prevent the misuse of DMs.
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。
