25 accepted papers
The proliferation of diverse data across users and organizations has driven the development of machine learning methods that enable multiple entities to jointly train models while minimizing data sharing. Among these, *multitask learning* (MTL) is a powerful paradigm that leverages similarities amon…
In machine learning, data curation is used to select the most valuable data for improving both model accuracy and computational efficiency. Recently, curation has also been explored as a solution for private machine learning: rather than training directly on sensitive data, which is known to leak in…
In this work, we show that it is possible to extract significant amounts of alignment training data from a post-trained model -- useful to steer the model to improve certain capabilities such as long-context reasoning, safety, instruction following, and maths. While the majority of related work on m…
Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has become the standard solution to bound leakage from the models.…
It is now common to evaluate Large Language Models (LLMs) by having humans manually vote to evaluate model outputs, in contrast to typical benchmarks that evaluate knowledge or skill at some particular task. Chatbot Arena, the most popular benchmark of this type, ranks models by asking users to sele…
State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models (LLMs). As a result, prior research has either relied on weaker attacks that avoid training references (e.g., fine-tu…
An important question today is whether a given text was used to train a large language model (LLM). A completion test is often employed: check if the LLM completes a sufficiently complex text. This, however, requires a ground-truth definition of membership; most commonly, it is defined as a member b…
"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often invoked as a solution for removing the effects of specific infor…
Many stakeholders---from model developers to policymakers---seek to minimize the risks of large language models (LLMs). Key to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are customizable via fine-tuning or when model weights are openly available. Severa…
Due to the sensitive nature of personally identifiable information (PII), its owners may have the authority to control its inclusion or request its removal from large-language model (LLM) training. Beyond this, PII may be added or removed from training datasets due to evolving dataset curation techn…
Large language models are prone to *memorizing* some of their training data. Memorized (and possibly sensitive) samples can then be extracted at generation time by adversarial or benign users. There is hope that *model alignment*---a standard training process that tunes a model to harmlessly follow…
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 he…
Differential privacy (DP) offers a theoretical upper bound on the potential privacy leakage of an algorithm, while empirical auditing establishes a practical lower bound. Auditing techniques exist for DP training algorithms. However machine learning can also be made private at inference. We propose…
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. [1], which attack automatic speech recognition (ASR) models by requesting a transcript of an utterance wh…
We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like OpenAI's ChatGPT or Google's PaLM-2. Specifically, our attack recovers the embedding projection layer (up to symmetries) of a transformer model, given typical API…
We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable, making them difficult to directly DP-train with since common tech…
Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but refuse to answer requests that could cause harm. However, adversarial users can construct inputs which circumvent attempts…
Modern neural language models that are widely used in various NLP tasks risk memorizing sensitive information from their training data. Understanding this memorization is important in real world applications and also from a learning-theoretical perspective. An open question in previous studies of la…
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 forgot…
We propose a scheme for auditing differentially private machine learning systems with a single training run. This exploits the parallelism of being able to add or remove multiple training examples independently. We analyze this using the connection between differential privacy and statistical genera…
Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing user data), degrades utility (repeated easy-to-memorize text…
Model distillation is frequently proposed as a technique to reduce the privacy leakage of machine learning. These empirical privacy defenses rely on the intuition that distilled ``student'' models protect the privacy of training data, as they only interact with this data indirectly through a ``teach…
Machine learning models trained on private datasets have been shown to leak their private data. Recent work has found that the average data point is rarely leaked---it is often the outlier samples that are subject to memorization and, consequently, leakage. We demonstrate and analyze an Onion Effect…
We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realistic privacy attacks. While previous work (Ma et al., arXiv 2019) proposed this co…
Motivated by settings in which predictive models may be required to be non-discriminatory with respect to certain attributes (such as race), but even collecting the sensitive attribute may be forbidden or restricted, we initiate the study of fair learning under the constraint of differential privacy…