ICLR 2025 论文列表

Unsupervised pre-training is a common step in developing computer vision models and large language models. In this setting, the absence of labels requires the use of similarity-based loss functions, such as the contrastive loss, that favor minimizing the distance between similar inputs and maximizing the distance between distinct inputs. As privacy concerns mount, training these models using differential privacy has become more important. However, due to how inputs are generated for these losses, one of their undesirable properties is that their $L_2$ sensitivity grows with the batch size. This property is particularly disadvantageous for differentially private training methods, such as DP-SGD. To overcome this issue, we develop a new DP-SGD variant for similarity based loss functions --- in particular, the commonly-used contrastive loss --- that manipulates gradients of the objective function in a novel way to obtain a sensitivity of the summed gradient that is $O(1)$ for batch size $n$. We test our DP-SGD variant on some CIFAR-10 pre-training and CIFAR-100 finetuning tasks and show that, in both tasks, our method's performance comes close to that of a non-private model and generally outperforms DP-SGD applied directly to the contrastive loss.

Multimodal Large Language Models (LLMs) are pivotal in revolutionizing customer support and operations by integrating multiple modalities such as text, images, and audio. Federated Prompt Learning (FPL) is a recently proposed approach that combines pre-trained multimodal LLMs such as vision-language models with federated learning to create personalized, privacy-preserving AI systems. However, balancing the competing goals of personalization, generalization, and privacy remains a significant challenge. Over-personalization can lead to overfitting, reducing generalizability, while stringent privacy measures, such as differential privacy, can hinder both personalization and generalization. In this paper, we propose a Differentially Private Federated Prompt Learning (DP-FPL) approach to tackle this challenge by leveraging a low-rank factorization scheme to capture generalization while maintaining a residual term that preserves expressiveness for personalization. To ensure privacy, we introduce a novel method where we apply local differential privacy to the two low-rank components of the local prompt, and global differential privacy to the global prompt. Our approach mitigates the impact of privacy noise on the model performance while balancing the tradeoff between personalization and generalization. Extensive experiments demonstrate the effectiveness of our approach over other benchmarks.

We propose a simple heuristic privacy analysis of noisy clipped stochastic gradient descent (DP-SGD) in the setting where only the last iterate is released and the intermediate iterates remain hidden. Namely, our heuristic assumes a linear structure for the model. We show experimentally that our heuristic is predictive of the outcome of privacy auditing applied to various training procedures. Thus it can be used prior to training as a rough estimate of the final privacy leakage. We also probe the limitations of our heuristic by providing some artificial counterexamples where it underestimates the privacy leakage. The standard composition-based privacy analysis of DP-SGD effectively assumes that the adversary has access to all intermediate iterates, which is often unrealistic. However, this analysis remains the state of the art in practice. While our heuristic does not replace a rigorous privacy analysis, it illustrates the large gap between the best theoretical upper bounds and the privacy auditing lower bounds and sets a target for further work to improve the theoretical privacy analyses.

Generative models must ensure both privacy and fairness for Trustworthy AI. While these goals have been pursued separately, recent studies propose to combine existing privacy and fairness techniques to achieve both goals. However, naively combining these techniques can be insufficient due to privacy-fairness conflicts, where a sample in a minority group may be represented in ways that support fairness, only to be suppressed for privacy. We demonstrate how these conflicts lead to adverse effects, such as privacy violations and unexpected fairness-utility tradeoffs. To mitigate these risks, we propose PFGuard, a generative framework with privacy and fairness safeguards, which simultaneously addresses privacy, fairness, and utility. By using an ensemble of multiple teacher models, PFGuard balances privacy-fairness conflicts between fair and private training stages and achieves high utility based on ensemble learning. Extensive experiments show that PFGuard successfully generates synthetic data on high-dimensional data while providing both DP guarantees and convergence in fair generative modeling.

Correlated noise mechanisms such as DP Matrix Factorization (DP-MF) have proven to be effective alternatives to DP-SGD in large-epsilon few-epoch training regimes. Significant work has been done to find the best correlated noise strategies, and the current state-of-the-art approach is DP-BandMF , which optimally balances the benefits of privacy amplification and noise correlation. Despite it's utility advantages, severe scalability limitations prevent this mechanism from handling large-scale training scenarios where the number of training iterations may be more than $10^4$ and the number of model parameters may exceed $10^7$. In this work, we present techniques to scale up DP-BandMF along these two dimensions, significantly extending it's reach and enabling it to effectively handle settings with over $10^6$ training iterations and $10^9$ model parameters, with no utility degradation at smaller scales.

Current techniques for privacy auditing of large language models (LLMs) have limited efficacy---they rely on basic approaches to generate canaries which leads to weak membership inference attacks that in turn give loose lower bounds on the empirical privacy leakage. We develop canaries that are far more effective than those used in prior work under threat models that cover a range of realistic settings. We demonstrate through extensive experiments on multiple families of fine-tuned LLMs that our approach sets a new standard for detection of privacy leakage. For measuring the memorization rate of non-privately trained LLMs, our designed canaries surpass prior approaches. For example, on the Qwen2.5-0.5B model, our designed canaries achieve $49.6\%$ TPR at $1\%$ FPR, vastly surpassing the prior approach's $4.2\%$ TPR at $1\%$ FPR. Our method can be used to provide a privacy audit of $\varepsilon \approx 1$ for a model trained with theoretical $\varepsilon$ of 4. To the best of our knowledge, this is the first time that a privacy audit of LLM training has achieved nontrivial auditing success in the setting where the attacker cannot train shadow models, insert gradient canaries, or access the model at every iteration.

Differential privacy (DP) is a privacy-preserving paradigm that protects the training data when training deep learning models. Critically, the performance of models is determined by the training hyperparameters, especially those of the learning rate schedule, thus requiring fine-grained hyperparameter tuning on the data. In practice, it is common to tune the learning rate hyperparameters through the grid search that (1) is computationally expensive as multiple runs are needed, and (2) increases the risk of data leakage as the selection of hyperparameters is data-dependent. In this work, we adapt the automatic learning rate schedule to DP optimization for any models and optimizers, so as to significantly mitigate or even eliminate the cost of hyperparameter tuning when applied together with automatic per-sample gradient clipping. Our hyperparameter-free DP optimization is almost as computationally efficient as the standard non-DP optimization, and achieves state-of-the-art DP performance on various language and vision tasks.

Patient data is widely used to estimate heterogeneous treatment effects and understand the effectiveness and safety of drugs. Yet, patient data includes highly sensitive information that must be kept private. In this work, we aim to estimate the conditional average treatment effect (CATE) from observational data under differential privacy. Specifically, we present DP-CATE, a novel framework for CATE estimation that is *Neyman-orthogonal* and ensures *differential privacy* of the estimates. Our framework is highly general: it applies to any two-stage CATE meta-learner with a Neyman-orthogonal loss function and any machine learning model can be used for nuisance estimation. We further provide an extension of our DP-CATE, where we employ RKHS regression to release the complete CATE function while ensuring differential privacy. We demonstrate the effectiveness of DP-CATE across various experiments using synthetic and real-world datasets. To the best of our knowledge, we are the first to provide a framework for CATE estimation that is doubly robust and differentially private.