相关论文: Towards Anonymous Neural Network Inference

The federated learning (FL) technique was developed to mitigate data privacy issues in the traditional machine learning paradigm. While FL ensures that a user's data always remain with the user, the gradients are shared with the centralized…

The widespread adoption of convolutional neural networks (CNNs) in resource-constrained scenarios has driven the development of Machine Learning as a Service (MLaaS) system. However, this approach is susceptible to privacy leakage, as the…

We propose Lockcoin, a secure and privacy-preserving mix service for bitcoin anonymity. We introduce mix servers to provide mix service for user to prevent attackers linking the input address with output address by using blind signature…

Deep neural networks (DNNs) have become core computation components within low latency Function as a Service (FaaS) prediction pipelines: including image recognition, object detection, natural language processing, speech synthesis, and…

Machine learning (ML) is increasingly used in network data planes for advanced traffic analysis, but existing solutions (such as FlowLens, N3IC, BoS) still struggle to simultaneously achieve low latency, high throughput, and high accuracy.…

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while…

Recently, deep learning as a service (DLaaS) has emerged as a promising way to facilitate the employment of deep neural networks (DNNs) for various purposes. However, using DLaaS also causes potential privacy leakage from both clients and…

Federated Learning (FL) enables collaborative model training without centralizing client data, making it attractive for privacy-sensitive domains. While existing approaches employ cryptographic techniques such as homomorphic encryption,…

The majority of financial organizations managing confidential data are aware of security threats and leverage widely accepted solutions (e.g., storage encryption, transport-level encryption, intrusion detection systems) to prevent or detect…

In an era of pervasive online surveillance, Internet users are in need of better anonymity solutions for online communications without sacrificing performance. Existing overlay anonymity tools, such as the Tor network, suffer from…

Privacy-preserving process mining enables the analysis of business processes using event logs, while giving guarantees on the protection of sensitive information on process stakeholders. To this end, existing approaches add noise to the…

This paper proposes Concurrent-Access Obfuscated Store (CAOS), a construction for remote data storage that provides access-pattern obfuscation in a honest-but-curious adversarial model, while allowing for low bandwidth overhead and client…

As large-scale quantum computers become a reality, they will likely exist as centralized cloud resources accessible to a broad user base. Securely delegating private quantum computations to untrusted servers is therefore a foundational…

This paper investigates under which conditions information can be reliably shared and consensus can be solved in unknown and anonymous message-passing networks that suffer from crash-failures. We provide algorithms to emulate registers and…

Secure aggregation enables federated learning (FL) to perform collaborative training of clients from local gradient updates without exposing raw data. However, existing secure aggregation schemes inevitably perform an expensive fresh setup…

We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages - (i) It is highly expressive with support for high capacity networks such…

Fully homomorphic encryption (FHE) enables private inference by evaluating neural networks on encrypted data. In this way, we can delegate the computation to a third party server without ever revealing the user's data. Currently, the CKKS…

Federated learning is known to be vulnerable to both security and privacy issues. Existing research has focused either on preventing poisoning attacks from users or on concealing the local model updates from the server, but not both.…

Recent work has demonstrated significant anonymity vulnerabilities in Bitcoin's networking stack. In particular, the current mechanism for broadcasting Bitcoin transactions allows third-party observers to link transactions to the IP…

Neuromorphic vision sensors offer low latency and high dynamic range, but their deployment in public spaces raises severe data protection concerns. Recent Event-to-Video (E2V) models can reconstruct high-fidelity intensity images from…