为测试时自适应引入差分隐私，保护数据隐私同时提升模型稳定性和准确率。
Private and Stable Test-Time Adaptation with Differential Privacy
- 将主流测试时自适应方法转化为差分隐私形式，采用逐样本梯度裁剪和高斯噪声。
- 在ImageNet-C上实现低隐私预算下准确率不降反升，且连续适应中更稳定。
- 仅带来轻微计算开销，适合关注隐私与鲁棒性平衡的研究者。
测试时自适应（TTA）通过在推理阶段更新模型来降低新数据上的误差。然而，这种更新会引发测试数据的隐私风险，因为模型参数依赖于所有历史输入。为控制该风险，我们将Tent、EATA、SAR、DeYO和COME等主流TTA方法转化为差分隐私（DP）形式，对每次更新应用逐样本梯度裁剪和高斯噪声。在ImageNet-C上，我们的DP-TTA方法在保持良好准确率的同时提供充分隐私保护；在低隐私预算下，梯度裁剪机制甚至能提升持续适应场景中的准确率与稳定性。这些隐私与性能的改进仅带来适度计算开销。本研究首次揭示了私有化测试时更新的重要性，推动更安全的测试时学习发展，并证实逐样本裁剪是提升适应准确率与稳定性的有效手段。
原文摘要 · Abstract (English)
Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference. However, these updates raise the issue of privacy w.r.t. the testing data, because the model parameters now depend on all past inputs. To control this privacy risk, we cast multiple popular TTA methods (Tent, EATA, SAR, DeYO, and COME) into differential privacy (DP) forms that apply per-sample gradient clipping and Gaussian noise for all updates. On ImageNet-C, our DP-TTA methods provide adequate privacy at small cost to accuracy, and in the low-privacy regime the clipping mechanism of DP can even improve the accuracy and stability of adaptation in the continual setting. These improvements to privacy and accuracy come at only modest computational overhead. These first results on private TTA raise awareness of the issue, inform the development of more private test-time updates, and identify per-sample clipping as an effective technique for improving the accuracy and stability of adaptation.
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。