战火中的定制化:文本到图像生态系统中的插件投毒
Customization under Fire: Plugin Poisoning in Text-to-Image Ecosystem
AI总结:
针对文本到图像生态系统中LoRA插件的供应链风险,提出PoisonLoRA方法,实现概念劫持和任务注入两种攻击,在多个数据集上达到近100%攻击成功率且难以被检测。
摘要:
文本到图像(T2I)模型的繁荣催生了一个以低秩适应(LoRA)插件为中心的充满活力的共享与使用生态系统,用户能够轻松定制和共享模型能力。然而,这种民主化伴随着隐藏但严重的安全风险。恶意用户可能共享和分发看似良性的LoRA插件,其中包含隐藏功能,以毒害模型共享市场(如Civitai或Liblib),严重破坏支撑该协作生态系统的用户信任,并威胁无数下游应用的安全。尽管存在这些风险,现实T2I生态系统中的插件投毒仍未得到充分研究。本文介绍了PoisonLoRA,这是首个针对LoRA插件供应链风险的系统性研究,利用了T2I生态系统中的信任和特性。我们识别出两种主要攻击实例:(1)概念劫持,劫持后的LoRA可生成图像以影响公众舆论和传播宣传;(2)任务注入,注入的LoRA仅在秘密密钥激活时产生有害内容(如NSFW图像)。关键的是,恶意负载具有病毒式传播特性。这种传播将创意协作行为(如LoRA合并)武器化以扩散其感染,使每次重混成为新的载体。大量实验验证了PoisonLoRA的有效性和隐蔽性。具体而言,我们在Civitai和Liblib上针对4个场景的6个数据集实现了约100%的攻击成功率(ASR),且未被平台检测到。投毒的LoRA表现出极强的鲁棒性,即使迁移到不同基础模型并重混超过5次,ASR仍接近100%。
英文摘要:
The prosperity of text-to-image (T2I) models has fostered a vibrant share-and-play ecosystem centered on Low-Rank Adaptation (LoRA) plugins, which allow users to customize and share model capabilities with ease. This democratization, however, comes with a hidden but severe security risk. Malicious users could share and distribute seemingly benign LoRA plugins that contain hidden functionalities to poison the model-sharing market, like Civitai or Liblib, severely undermining the user trust that underpins this collaborative ecosystem and threatening the safety of countless downstream applications. Despite these risks, plugin poisoning in the real-world T2I ecosystem remains underexplored. This paper introduces PoisonLoRA, the first systematic study of LoRA plugin supply-chain risks that exploits the trust and characteristics within the T2I ecosystem. We identify two primary attack instances: (1) Concept Hijacking, where a hijacked LoRA could generate images to influence public opinion and spread propaganda, and (2) Task Injection, where a LoRA is injected to produce harmful content (e.g., NSFW images) only activated by a secret key. Critically, the malicious payload persists with virus-like propagation. Such propagations weaponize the very act of creative collaboration (e.g., LoRA merging) to spread its contagion, turning every remix into a new carrier. Extensive experiments validate that PoisonLoRA is both effective and stealthy. Specifically, we achieve approximately 100% attack success rates (ASR) on both Civitai and Liblib on 6 datasets across 4 scenarios, without being detected by the platforms. The poisoned LoRA demonstrates extreme robustness, with nearly 100% ASR even transferred to different base models and remixed more than 5 times.
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。