Self-supervised learning (SSL) methods for large speech models have proven to be highly effective at ASR. With the interest in public deployment of large pre-trained models, there is a rising concern for unintended memorization and leakage of sensitive data points from the training data. In this paper, we apply differentially private (DP) pre-training to a SOTA Conformer-based encoder, and study its performance on a downstream ASR task assuming the fine-tuning data is public. This paper is the first to apply DP to SSL for ASR, investigating the DP noise tolerance of the BEST-RQ pre-training method. Notably, we introduce a novel variant of model pruning called gradient-based layer freezing that provides strong improvements in privacy-utility-compute trade-offs. Our approach yields a LibriSpeech test-clean/other WER (%) of 3.78/ 8.41 with ($10$, 1e^-9)-DP for extrapolation towards low dataset scales, and 2.81/ 5.89 with (10, 7.9e^-11)-DP for extrapolation towards high scales.

Gradient clipping plays a vital role in training large-scale automatic speech recognition (ASR) models. It is typically applied to minibatch gradients to prevent gradient explosion, and to the individual sample gradients to mitigate unintended memorization. This work systematically investigates the impact of a specific granularity of gradient clipping, namely per-core clip-ping (PCC), across training a wide range of ASR models. We empirically demonstrate that PCC can effectively mitigate unintended memorization in ASR models. Surprisingly, we find that PCC positively influences ASR performance metrics, leading to improved convergence rates and reduced word error rates. To avoid tuning the additional hyperparameter introduced by PCC, we further propose a novel variant, adaptive per-core clipping (APCC), for streamlined optimization. Our findings highlight the multifaceted benefits of PCC as a strategy for robust, privacy-forward ASR model training.

Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech recognition (ASR) models by requesting a transcript of an utterance which is partially replaced with noise. They show that when a record has been seen at training time, the model will transcribe the noisy record with its memorized sensitive transcript. In our work, we extend these attacks beyond ASR models, to attack pretrained speech encoders. Our method fine-tunes the encoder to produce an ASR model, and then performs noise masking on this model, which we find recovers private information from the pretraining data, despite the model never having seen transcripts at pretraining time! We show how to improve the precision of these attacks and investigate a number of countermeasures to our attacks.

It is well-known that neural networks can unintentionally memorize their training examples, causing privacy concerns. However, auditing memorization in large non-auto-regressive automatic speech recognition (ASR) models has been challenging due to the high compute cost of existing methods such as hardness calibration. In this work, we design a simple auditing method to measure memorization in large ASR models without the extra compute overhead. Concretely, we speed up randomly-generated utterances to create a mapping between vocal and text information that is difficult to learn from typical training examples. Hence, accurate predictions only for sped-up training examples can serve as clear evidence for memorization, and the corresponding accuracy can be used to measure memorization. Using the proposed method, we showcase memorization in the state-of-the-art ASR models. To mitigate memorization, we tried gradient clipping during training to bound the influence of any individual example on the final model. We empirically show that clipping each example's gradient can mitigate memorization for sped-up training examples with up to 16 repetitions in the training set. Furthermore, we show that in large-scale distributed training, clipping the average gradient on each compute core maintains neutral model quality and compute cost while providing strong privacy protection.

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In forgetting, examples which appeared early in training are forgotten by the end. In this work, we connect these phenomena. We propose a technique to measure to what extent models "forget" the specifics of training examples, becoming less susceptible to privacy attacks on examples they have not seen recently. We show that, while non-convex models can memorize data forever in the worst-case, standard image, speech, and language models empirically do forget examples over time. We identify nondeterminism as a potential explanation, showing that deterministically trained models do not forget. Our results suggest that examples seen early when training with extremely large datasets - for instance those examples used to pre-train a model - may observe privacy benefits at the expense of examples seen later.

In the privacy-utility tradeoff of a model trained on benchmark language and vision tasks, remarkable improvements have been widely reported with the use of pretraining on publicly available data. This is in part due to the benefits of transfer learning, which is the standard motivation for pretraining in non-private settings. However, the stark contrast in the improvement achieved through pretraining under privacy compared to non-private settings suggests that there may be a deeper, distinct cause driving these gains. To explain this phenomenon, we hypothesize that the non-convex loss landscape of a model training necessitates an optimization algorithm to go through two phases. In the first, the algorithm needs to select a good "basin" in the loss landscape. In the second, the algorithm solves an easy optimization within that basin. The former is a harder problem to solve with private data, while the latter is harder to solve with public data due to a distribution shift or data scarcity. Guided by this intuition, we provide theoretical constructions that provably demonstrate the separation between private training with and without public pretraining. Further, systematic experiments on CIFAR10 and LibriSpeech provide supporting evidence for our hypothesis.

Hyperparameter optimization is a ubiquitous challenge in machine learning, and the performance of a trained model depends crucially upon their effective selection. While a rich set of tools exist for this purpose, there are currently no practical hyperparameter selection methods under the constraint of differential privacy (DP). We study honest hyperparameter selection for differentially private machine learning, in which the process of hyperparameter tuning is accounted for in the overall privacy budget. To this end, we i) show that standard composition tools outperform more advanced techniques in many settings, ii) empirically and theoretically demonstrate an intrinsic connection between the learning rate and clipping norm hyperparameters, iii) show that adaptive optimizers like DPAdam enjoy a significant advantage in the process of honest hyperparameter tuning, and iv) draw upon novel limiting behaviour of Adam in the DP setting to design a new and more efficient optimizer.

This paper presents the first consumer-scale next-word prediction (NWP) model trained with Federated Learning (FL) while leveraging the Differentially Private Federated Averaging (DP-FedAvg) technique. There has been prior work on building practical FL infrastructure, including work demonstrating the feasibility of training language models on mobile devices using such infrastructure. It has also been shown (in simulations on a public corpus) that it is possible to train NWP models with user-level differential privacy using the DP-FedAvg algorithm. Nevertheless, training production-quality NWP models with DP-FedAvg in a real-world production environment on a heterogeneous fleet of mobile phones requires addressing numerous challenges. For instance, the coordinating central server has to keep track of the devices available at the start of each round and sample devices uniformly at random from them, while ensuring \emph{secrecy of the sample}, etc. Unlike all prior privacy-focused FL work of which we are aware, for the first time we demonstrate the deployment of a differentially private mechanism for the training of a production neural network in FL, as well as the instrumentation of the production training infrastructure to perform an end-to-end empirical measurement of unintended memorization.

Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fundamental building block in many applications for learning over sensitive data. Two standard approaches, privacy amplification by subsampling, and privacy amplification by shuffling, permit adding lower noise in DP-SGD than via na\"{\i}ve schemes. A key assumption in both these approaches is that the elements in the data set can be uniformly sampled, or be uniformly permuted -- constraints that may become prohibitive when the data is processed in a decentralized or distributed fashion. In this paper, we focus on conducting iterative methods like DP-SGD in the setting of federated learning (FL) wherein the data is distributed among many devices (clients). Our main contribution is the \emph{random check-in} distributed protocol, which crucially relies only on randomized participation decisions made locally and independently by each client. It has privacy/accuracy trade-offs similar to privacy amplification by subsampling/shuffling. However, our method does not require server-initiated communication, or even knowledge of the population size. To our knowledge, this is the first privacy amplification tailored for a distributed learning framework, and it may have broader applicability beyond FL. Along the way, we extend privacy amplification by shuffling to incorporate $(\epsilon,\delta)$-DP local randomizers, and exponentially improve its guarantees. In practical regimes, this improvement allows for similar privacy and utility using data from an order of magnitude fewer users.

Recent works have shown that generative sequence models (e.g., language models) have a tendency to memorize rare or unique sequences in the training data. Since useful models are often trained on sensitive data, to ensure the privacy of the training data it is critical to identify and mitigate such unintended memorization. Federated Learning (FL) has emerged as a novel framework for large-scale distributed learning tasks. However, it differs in many aspects from the well-studied central learning setting where all the data is stored at the central server. In this paper, we initiate a formal study to understand the effect of different components of canonical FL on unintended memorization in trained models, comparing with the central learning setting. Our results show that several differing components of FL play an important role in reducing unintended memorization. Specifically, we observe that the clustering of data according to users---which happens by design in FL---has a significant effect in reducing such memorization, and using the method of Federated Averaging for training causes a further reduction. We also show that training with a strong user-level differential privacy guarantee results in models that exhibit the least amount of unintended memorization.