BadGraph: 针对文本引导图生成的潜在扩散模型后门攻击
BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation
AI总结：
本文提出BadGraph，一种针对文本引导图生成的潜在扩散模型的后门攻击方法，通过文本触发器污染训练数据，在推理时触发指定子图，同时保持对清洁输入的正常性能。
摘要：
图生成的快速发展引发了新的安全担忧，特别是后门漏洞。尽管先前工作探讨了图像扩散和无条件图生成中的后门攻击，但条件，尤其是文本引导的图生成仍鲜有研究。本文提出BadGraph，一种针对文本引导图生成的潜在扩散模型的后门攻击方法。BadGraph利用文本触发器污染训练数据，隐蔽地植入后门，在触发时诱导攻击者指定的子图，同时在清洁输入上保持正常性能。在四个基准数据集（PubChem、ChEBI-20、PCDes、MoMu）上的广泛实验展示了攻击的有效性和隐蔽性：少于10%的污染率可实现50%的攻击成功率，而24%足以达到超过80%的成功率，对良性样本的性能降解 negligible。消融研究进一步揭示后门是在VAE和扩散训练期间植入的，而非预训练。这些发现揭示了文本引导图生成潜在扩散模型的安全漏洞，突显了模型在药物发现等应用中的严重风险，并强调了对这类扩散模型后门攻击的鲁棒防御需求。
英文摘要：
The rapid progress of graph generation has raised new security concerns, particularly regarding backdoor vulnerabilities. While prior work has explored backdoor attacks in image diffusion and unconditional graph generation, conditional, especially text-guided graph generation remains largely unexamined. This paper proposes BadGraph, a backdoor attack method against latent diffusion models for text-guided graph generation. BadGraph leverages textual triggers to poison training data, covertly implanting backdoors that induce attacker-specified subgraphs during inference when triggers appear, while preserving normal performance on clean inputs. Extensive experiments on four benchmark datasets (PubChem, ChEBI-20, PCDes, MoMu) demonstrate the effectiveness and stealth of the attack: less than 10% poisoning rate can achieves 50% attack success rate, while 24% suffices for over 80% success rate, with negligible performance degradation on benign samples. Ablation studies further reveal that the backdoor is implanted during VAE and diffusion training rather than pretraining. These findings reveal the security vulnerabilities in latent diffusion models of text-guided graph generation, highlight the serious risks in models' applications such as drug discovery and underscore the need for robust defenses against the backdoor attack in such diffusion models.
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。
