GIFT让扩散模型免疫恶意微调，还能保留生成安全内容的能力。
GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention
- 通过梯度感知的双层优化，噪声化有害概念表示并保护安全数据表现。
- 在恶意微调后，模型重学有害概念的能力显著下降，安全生成性能保持稳定。
- 适合关注生成模型安全防御的研究者与开发者使用。
我们提出 GIFT：一种梯度感知的免疫技术，用于防御扩散模型在恶意微调下的攻击，同时保留其生成安全内容的能力。现有安全机制如安全检测器易被绕过，概念擦除方法在对抗性微调下失效。GIFT 将免疫过程建模为双层优化问题：上层目标通过表示噪声和最大化，削弱模型对有害概念的表征能力；下层目标则保持对安全数据的生成性能。实验表明，该方法能显著抑制模型在恶意微调后重新学习有害概念的能力，同时维持安全生成质量，为构建抗对抗性微调攻击的内在安全生成模型提供了新方向。
原文摘要 · Abstract (English)
We present GIFT: a {G}radient-aware {I}mmunization technique to defend diffusion models against malicious {F}ine-{T}uning while preserving their ability to generate safe content. Existing safety mechanisms like safety checkers are easily bypassed, and concept erasure methods fail under adversarial fine-tuning. GIFT addresses this by framing immunization as a bi-level optimization problem: the upper-level objective degrades the model's ability to represent harmful concepts using representation noising and maximization, while the lower-level objective preserves performance on safe data. GIFT achieves robust resistance to malicious fine-tuning while maintaining safe generative quality. Experimental results show that our method significantly impairs the model's ability to re-learn harmful concepts while maintaining performance on safe content, offering a promising direction for creating inherently safer generative models resistant to adversarial fine-tuning attacks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。