相关论文: CrypTFlow: Secure TensorFlow Inference

SAFE is a clean-slate design for a highly secure computer system, with pervasive mechanisms for tracking and limiting information flows. At the lowest level, the SAFE hardware supports fine-grained programmable tags, with efficient and…

In this work, we present an efficient secure multi-party computation MPC protocol that provides strong security guarantees in settings with dishonest majority of participants who may behave arbitrarily. Unlike the popular MPC implementation…

ML-as-a-service continues to grow, and so does the need for very strong privacy guarantees. Secure inference has emerged as a potential solution, wherein cryptographic primitives allow inference without revealing users' inputs to a model…

Computing systems, including real-time embedded systems, are becoming increasingly connected to allow for more advanced and safer operation. Such embedded systems are resource-constrained, such as lower processing capabilities, as compared…

Transformer inference in machine-learning-as-a-service (MLaaS) raises privacy concerns for sensitive user inputs. Prior secure solutions that combine fully homomorphic encryption (FHE) and secure multiparty computation (MPC) are…

We describe scalable protocols for solving the secure multi-party computation (MPC) problem among a large number of parties. We consider both the synchronous and the asynchronous communication models. In the synchronous setting, our…

TensorFlow is an open-source framework for deep learning dataflow and contains application programming interfaces (APIs) of voice analysis, natural language process, and computer vision. Especially, TensorFlow object detection API in…

Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Despite their growing capabilities, today's agent frameworks…

Many inference services based on large language models (LLMs) pose a privacy concern, either revealing user prompts to the service or the proprietary weights to the user. Secure inference offers a solution to this problem through secure…

We propose an efficient framework for enabling secure multi-party numerical computations in a Peer-to-Peer network. This problem arises in a range of applications such as collaborative filtering, distributed computation of trust and…

Remote procedure call (RPC) is the backbone of many modern distributed systems. Google's gRPC is one of the most popular open source RPC frameworks available in the community. gRPC is the main communication engine for Google's Deep Learning…

Large-scale deep learning benefits from an emerging class of AI accelerators. Some of these accelerators' designs are general enough for compute-intensive applications beyond AI and Cloud TPU is one such example. In this paper, we…

Model Context Protocol (MCP) have quickly become the interface layer between LLM agents and external tools, yet they also introduce unsafe data flows that existing analyzers handle poorly. Vulnerabilities manifest in two directions:…

Novel machine learning computational tools open new perspectives for quantum information systems. Here we adopt the open-source programming library TensorFlow to design multi-level quantum gates including a computing reservoir represented…

The security in information-flow has become a major concern for cyber-physical systems (CPSs). In this work, we focus on the analysis of an information-flow security property, called opacity. Opacity characterizes the plausible deniability…

Due to the rising privacy concerns on sensitive client data and trained models like Transformers, secure multi-party computation (MPC) techniques are employed to enable secure inference despite attendant overhead. Existing works attempt to…

Secure multi-party computation (SMPC) protocols allow several parties that distrust each other to collectively compute a function on their inputs. In this paper, we introduce a protocol that lifts classical SMPC to quantum SMPC in a…

Generating secure random numbers is a central problem in cryptography that needs a reliable source of enough computing entropy. Without enough entropy available - meaning no good source of secure random numbers - a device is susceptible to…

Control-flow attestation unifies the worlds of control-flow integrity and platform attestation by measuring and reporting a target's run-time behaviour to a verifier. Trust assurances in the target are provided by testing whether its…

The emergence of cloud computing provides a new computing paradigm for users -- massive and complex computing tasks can be outsourced to cloud servers. However, the privacy issues also follow. Fully homomorphic encryption shows great…