arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.04898cs.CRcs.AI
收藏

针对文本到图像扩散模型的语义级后门攻击

Semantic-level Backdoor Attack against Text-to-Image Diffusion Models

College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China(复旦大学计算机科学与人工智能学院,上海,中国);State Key Laboratory of Integrated Services Networks, Xidian University, Xian, China(集成服务网络国家重点实验室,西安电子科技大学,西安,中国);University of Electronic Science and Technology of China, Sichuan, China(电子科技大学,四川,中国);Ajou University, Gyeonggi-do, South Korea(庆尚道,韩国,全州大学)

Tianxin Chen, Wenbo Jiang, Hongqiao Chen, Zhirun Zheng, Cheng Huang

AI总结:

提出语义级后门攻击(SemBD),通过基于连续语义区域的表示级触发器替代离散文本模式,利用蒸馏编辑交叉注意力层的键和值投影矩阵植入后门,并引入语义正则化和多实体后门目标增强隐蔽性,实现100%攻击成功率并抵御输入级防御。

摘要:

文本到图像(T2I)扩散模型因其强大的生成能力而被广泛采用,但仍易受到后门攻击。现有攻击通常依赖于固定的文本触发器和单实体后门目标,使其极易受到基于枚举的输入防御和注意力一致性检测的攻击。在这项工作中,我们提出了语义级后门攻击(SemBD),它引入了基于连续语义区域而非离散文本模式的表示级触发器。SemBD通过基于蒸馏编辑交叉注意力层中的键和值投影矩阵来植入此类语义后门,使得语义等价但文本多样的提示能够激活后门。为了进一步增强隐蔽性,SemBD引入了语义正则化以防止在不完整语义下的意外激活,以及避免高度一致交叉注意力模式的多实体后门目标。大量实验表明,SemBD实现了100%的攻击成功率,同时保持了对最先进输入级防御的强鲁棒性。我们的代码可在https://github.com/DPAS-Lab/SemBD/获取。

英文摘要:

Text-to-image (T2I) diffusion models are widely adopted for their strong generative capabilities, yet remain vulnerable to backdoor attacks. Existing attacks typically rely on fixed textual triggers and single-entity backdoor targets, making them highly susceptible to enumeration-based input defenses and attention-consistency detection. In this work, we propose Semantic-level Backdoor Attack (SemBD), which introduces representation-level triggers based on continuous semantic regions rather than discrete textual patterns. SemBD implants such semantic backdoors by distillation-based editing of the key and value projection matrices in cross-attention layers, enabling semantically equivalent but textually diverse prompts to activate the backdoor. To further enhance stealthiness, SemBD incorporates a semantic regularization to prevent unintended activation under incomplete semantics, as well as multi-entity backdoor targets that avoid highly consistent cross-attention patterns. Extensive experiments demonstrate that SemBD achieves a 100% attack success rate while maintaining strong robustness against state-of-the-art input-level defenses. Our code is available at https://github.com/DPAS-Lab/SemBD/.

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。

↑