Related papers: Validation of GPU Computation in Decentralized, Tr…

Recent developments in Machine Learning and Deep Learning depend heavily on cloud computing and specialized hardware, such as GPUs and TPUs. This forces those using those models to trust private data to cloud servers. Such scenario has…

Confidential computing has gained prominence due to the escalating volume of data-driven applications (e.g., machine learning and big data) and the acute desire for secure processing of sensitive data, particularly, across distributed…

Researchers have developed neural network verification algorithms motivated by the need to characterize the robustness of deep neural networks. The verifiers aspire to answer whether a neural network guarantees certain properties with…

We present Argos, a simple approach for adding verifiability to fully homomorphic encryption (FHE) schemes using trusted hardware. Traditional approaches to verifiable FHE require expensive cryptographic proofs, which incur an overhead of…

The neural network has become an integral part of modern software systems. However, they still suffer from various problems, in particular, vulnerability to adversarial attacks. In this work, we present a novel program reasoning framework…

We consider the parameterized verification problem for distributed algorithms where the goal is to develop techniques to prove the correctness of a given algorithm regardless of the number of participating processes. Motivated by an…

Due to significant improvements in performance in recent years, neural networks are currently used for an ever-increasing number of applications. However, neural networks have the drawback that their decisions are not readily interpretable…

In this paper, we consider the computational complexity of formally verifying the behavior of Rectified Linear Unit (ReLU) Neural Networks (NNs), where verification entails determining whether the NN satisfies convex polytopic…

We present and experimentally demonstrate a novel approach to verification and benchmarking of quantum computing, implementing it on an ion-trap quantum computer. Unlike previous information-theoretically secure verification protocols,…

This paper investigates the algorithmic safety verification problem of infinite-state parameterized concurrent programs over a rich set of communication topologies. The goal is to automatically produce a proof of correctness in the form of…

With the advent of cloud-based quantum computing, it has become vital to provide strong guarantees that computations delegated by clients to quantum service providers have been executed faithfully. Secure - blind and verifiable - Delegated…

In this paper, a secure Convolutional Neural Network classifier is proposed using Fully Homomorphic Encryption (FHE). The secure classifier provides a user with the ability to out-source the computations to a powerful cloud server and/or…

Fully-homomorphic encryption (FHE) enables computation on encrypted data while maintaining secrecy. Recent research has shown that such schemes exist even for quantum computation. Given the numerous applications of classical FHE…

Secure function evaluation (SFE) is the process of computing a function (or running an algorithm) on some data, while keeping the input, output and intermediate results hidden from the environment in which the function is evaluated. This…

Matrix decompositions are ubiquitous in machine learning, including applications in dimensionality reduction, data compression and deep learning algorithms. Typical solutions for matrix decompositions have polynomial complexity which…

We present IPU Trusted Extensions (ITX), a set of experimental hardware extensions that enable trusted execution environments in Graphcore's AI accelerators. ITX enables the execution of AI workloads with strong confidentiality and…

GPUs are playing an increasingly important role in general-purpose computing. Many algorithms require synchronizations at different levels of granularity in a single GPU. Additionally, the emergence of dense GPU nodes also calls for…

We present efficient and practical algorithms for a large, distributed system of processors to achieve reliable computations in a secure manner. Specifically, we address the problem of computing a general function of several private inputs…

The security of blockchain systems is fundamentally based on the decentralized consensus in which the majority of parties behave honestly, and the content verification process is essential to maintaining the robustness of blockchain…

In the last decade, a large body of work has emerged on robustness of neural networks, i.e., checking if the decision remains unchanged when the input is slightly perturbed. However, most of these approaches ignore the confidence of a…