Related papers: Disparate Impact on Group Accuracy of Linearizatio…
Private inference (PI) enables inference directly on cryptographically secure data.While promising to address many privacy issues, it has seen limited use due to extreme runtimes. Unlike plaintext inference, where latency is dominated by…
The recent rise of privacy concerns has led researchers to devise methods for private neural inference -- where inferences are made directly on encrypted data, never seeing inputs. The primary challenge facing private inference is that…
Privacy-Preserving Machine Learning algorithms must balance classification accuracy with data privacy. This can be done using a combination of cryptographic and machine learning tools such as Convolutional Neural Networks (CNN). CNNs…
The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce ReLU operations often involve manual effort and sacrifice…
The growing concern about data privacy has led to the development of private inference (PI) frameworks in client-server applications which protects both data privacy and model IP. However, the cryptographic primitives required yield…
ReLU activations are the main bottleneck in Private Inference that is based on ResNet networks. This is because they incur significant inference latency. Reducing ReLU count is a discrete optimization problem, and there are two common ways…
The performance cost of differential privacy has, for some applications, been shown to be higher for minority groups; fairness, conversely, has been shown to disproportionally compromise the privacy of members of such groups. Most work in…
Private computation of nonlinear functions, such as Rectified Linear Units (ReLUs) and max-pooling operations, in deep neural networks (DNNs) poses significant challenges in terms of storage, bandwidth, and time consumption. To address…
Machine learning as a service has given raise to privacy concerns surrounding clients' data and providers' models and has catalyzed research in private inference (PI): methods to process inferences without disclosing inputs. Recently,…
Outsourcing deep neural networks (DNNs) inference tasks to an untrusted cloud raises data privacy and integrity concerns. While there are many techniques to ensure privacy and integrity for polynomial-based computations, DNNs involve…
We theoretically study how differential privacy interacts with both individual and group fairness in binary linear classification. More precisely, we focus on the output perturbation mechanism, a classic approach in privacy-preserving…
The simultaneous rise of machine learning as a service and concerns over user privacy have increasingly motivated the need for private inference (PI). While recent work demonstrates PI is possible using cryptographic primitives, the…
Neural networks trained on real-world data often exhibit biases while simultaneously being vulnerable to privacy attacks aimed at extracting sensitive information. Despite extensive research on each problem individually, their intersection…
Algorithmic fairness and privacy are essential pillars of trustworthy machine learning. Fair machine learning aims at minimizing discrimination against protected groups by, for example, imposing a constraint on models to equalize their…
We consider the problem of fitting a linear model to data held by individuals who are concerned about their privacy. Incentivizing most players to truthfully report their data to the analyst constrains our design to mechanisms that provide…
Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful full-precision training and binary training. We bring some insights about why this…
Prior work on Private Inference (PI) -- inferences performed directly on encrypted input -- has focused on minimizing a network's ReLUs, which have been assumed to dominate PI latency rather than FLOPs. Recent work has shown that FLOPs for…
This article measures how sparsity can make neural networks more robust to membership inference attacks. The obtained empirical results show that sparsity improves the privacy of the network, while preserving comparable performances on the…
The emergence of deep learning has been accompanied by privacy concerns surrounding users' data and service providers' models. We focus on private inference (PI), where the goal is to perform inference on a user's data sample using a…
Machine learning (ML) algorithms are heavily based on the availability of training data, which, depending on the domain, often includes sensitive information about data providers. This raises critical privacy concerns. Anonymization…