In-context learning (ICL)-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models. While recent works have investigated the mechanisms underlying ICL, its feasibility under formal privacy constraints remains largely unexplored. In this paper, we propose a differentially private pretraining algorithm for linear attention heads and present the first theoretical analysis of the privacy-accuracy trade-off for ICL in linear regression. Our results characterize the fundamental tension between optimization and privacy-induced noise, formally capturing behaviors observed in private training via iterative methods. Additionally, we show that our method is robust to adversarial perturbations of training prompts, unlike standard ridge regression. All theoretical findings are supported by extensive simulations across diverse settings.

本研究解决了上下文学习（ICL）在正式隐私约束下的可行性问题，提出了一种差分隐私预训练算法并进行理论分析。研究发现，优化与隐私引入的噪声之间存在基本的矛盾，并且该方法在训练提示的对抗干扰下表现出鲁棒性，具有重要的实践意义。

你的注意力有多私密？隐私与上下文学习的桥梁