提出让模型难微调的反向训练方法，保护特定类别不被滥用。
Learning to Obstruct Few-Shot Image Classification over Restricted Classes
- 通过元学习让预训练模型对特定任务初始化不良
- 在三数据集上成功阻碍四种少样本分类方法
- 适合关注模型安全与滥用防护的研究者
开源预训练模型的普及使得微调新任务变得容易，但也带来潜在风险，如恶意方开发有害应用。本文探讨能否构建一种预训练模型，使其难以针对某些下游任务进行微调。聚焦于少样本图像分类（FSC），研究如何使模型对一组受限类别更难微调，同时保持其他类别的性能。提出学习阻碍（LTO）算法，通过元学习方式调整预训练骨干网络，使其成为‘差的初始值’。实验表明，LTO在三个数据集（ImageNet、CIFAR100和CelebA）上成功阻碍了四种FSC方法，验证了其有效性。
原文摘要 · Abstract (English)
Advancements in open-source pre-trained backbones make it relatively easy to fine-tune a model for new tasks. However, this lowered entry barrier poses potential risks, e.g., bad actors developing models for harmful applications. A question arises: Is possible to develop a pre-trained model that is difficult to fine-tune for certain downstream tasks? To begin studying this, we focus on few-shot classification (FSC). Specifically, we investigate methods to make FSC more challenging for a set of restricted classes while maintaining the performance of other classes. We propose to meta-learn over the pre-trained backbone in a manner that renders it a ''poor initialization''. Our proposed Learning to Obstruct (LTO) algorithm successfully obstructs four FSC methods across three datasets, including ImageNet and CIFAR100 for image classification, as well as CelebA for attribute classification.
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。