Search for: All records

Data valuation, a growing field that aims at quantifying the usefulness of individual data sources for training machine learning (ML) models, faces notable yet often overlooked privacy challenges. This paper studies these challenges with a focus on KNN-Shapley, one of the most practical data valuation methods nowadays. We first emphasize the inherent privacy risks of KNN-Shapley, and demonstrate the significant technical challenges in adapting KNN-Shapley to accommodate differential privacy (DP). To overcome these challenges, we introduce TKNN-Shapley, a refined variant of KNN-Shapley that is privacy-friendly, allowing for straightforward modifications to incorporate DP guarantee (DP-TKNN-Shapley). We show that DP-TKNN-Shapley has several advantages and offers a superior privacy-utility tradeoff compared to naively privatized KNN-Shapley. Moreover, even non-private TKNN-Shapley matches KNN-Shapley's performance in discerning data quality. Overall, our findings suggest that TKNN-Shapley is a promising alternative to KNN-Shapley, particularly for real-world applications involving sensitive data. 

Label differential privacy is a relaxation of differential privacy for machine learning scenarios where the labels are the only sensitive information that needs to be protected in the training data. For example, imagine a survey from a participant in a university class about their vaccination status. Some attributes of the students are publicly available but their vaccination status is sensitive information and must remain private. Now if we want to train a model that predicts whether a student has received vaccination using only their public information, we can use label-DP. Recent works on label-DP use different ways of adding noise to the labels in order to obtain label-DP models. In this work, we present novel techniques for training models with label-DP guarantees by leveraging unsupervised learning and semi-supervised learning, enabling us to inject less noise while obtaining the same privacy, therefore achieving a better utility-privacy trade-off. We first introduce a framework that starts with an unsupervised classifier f0 and dataset D with noisy label set Y , reduces the noise in Y using f0 , and then trains a new model f using the less noisy dataset. Our noise reduction strategy uses the model f0 to remove the noisy labels that are incorrect with high probability. Then we use semi-supervised learning to train a model using the remaining labels. We instantiate this framework with multiple ways of obtaining the noisy labels and also the base classifier. As an alternative way to reduce the noise, we explore the effect of using unsupervised learning: we only add noise to a majority voting step for associating the learned clusters with a cluster label (as opposed to adding noise to individual labels); the reduced sensitivity enables us to add less noise. Our experiments show that these techniques can significantly outperform the prior works on label-DP. 

An attacker can obtain a valid TLS certificate for a domain by hijacking communication between a certificate authority (CA) and a victim domain. Performing domain validation from multiple vantage points can defend against these attacks. We explore the design space of multi-vantage-point domain validation to achieve (1) security via sufficiently diverse vantage points, (2) performance by ensuring low latency and overhead in certificate issuance, (3) manageability by complying with CA/Browser forum requirements, and requiring minimal changes to CA operations, and (4) a low benign failure rate for legitimate requests. Our opensource implementation was deployed by the Let's Encrypt CA in February 2020, and has since secured the issuance of more than half a billion certificates during the first year of its deployment. Using real-world operational data from Let's Encrypt, we show that our approach has negligible latency and communication overhead, and a benign failure rate comparable to conventional designs with one vantage point. Finally, we evaluate the security improvements using a combination of ethically conducted real-world BGP hijacks, Internet-scale traceroute experiments, and a novel BGP simulation framework. We show that multi-vantage-point domain validation can thwart the vast majority of BGP attacks. Our work motivates the deployment of multi-vantage-point domain validation across the CA ecosystem to strengthen TLS certificate issuance and user privacy.