Related papers: Trustless Audits without Revealing Data or Models

Auditing the information leakage of latent sensitive features during the transborder data flow has attracted sufficient attention from global digital regulators. However, there is missing a technical approach for the audit practice due to…

Federated learning is a machine learning setting where a set of edge devices collaboratively train a model under the orchestration of a central server without sharing their local data. At each communication round of federated learning, edge…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

With increasing concerns over data privacy and model copyrights, especially in the context of collaborations between AI service providers and data owners, an innovative SG-ZSL paradigm is proposed in this work. SG-ZSL is designed to foster…

Federated knowledge discovery and data mining are challenged to assess the trustworthiness of data originating from autonomous sources while protecting confidentiality and privacy. Truth-finding algorithms help corroborate data from…

As the deployment of deep learning models continues to expand across industries, the threat of malicious incursions aimed at gaining access to these deployed models is on the rise. Should an attacker gain access to a deployed model, whether…

We present a framework that allows to certify the fairness degree of a model based on an interactive and privacy-preserving test. The framework verifies any trained model, regardless of its training process and architecture. Thus, it allows…

Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…

We live in an era of information and it is very important to handle the exchange of information. While sending data to an authorized source, we need to protect it from unauthorized sources, changes, and authentication. ZKP technique can be…

We consider a type of zero-knowledge protocols that are of interest for their practical applications within networks like the Internet: efficient zero-knowledge arguments of knowledge that remain secure against concurrent man-in-the-middle…

The rapid integration of AI-powered coding assistants into developer workflows has raised significant privacy and trust concerns. As developers entrust proprietary code to services like OpenAI's GPT, Google's Gemini, and GitHub Copilot, the…

Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy estimate (nearly)…

Deploying Machine Learning as a Service gives rise to model plagiarism, leading to copyright infringement. Ownership testing techniques are designed to identify model fingerprints for verifying plagiarism. However, previous works often rely…

A deep learning model usually has to sacrifice some utilities when it acquires some other abilities or characteristics. Privacy preservation has such trade-off relationships with utilities. The loss disparity between various defense…

With the ever-growing data and the need for developing powerful machine learning models, data owners increasingly depend on various untrusted platforms (e.g., public clouds, edges, and machine learning service providers) for scalable…

The rapid expansion of Artificial Intelligence is hindered by a fundamental friction in data markets: the value-privacy dilemma, where buyers cannot verify a dataset's utility without inspection, yet inspection may expose the data (Arrow's…

This paper proposes a new approach for privacy-preserving and verifiable convolutional neural network (CNN) testing, enabling a CNN model developer to convince a user of the truthful CNN performance over non-public data from multiple…

Federated learning (FL) enables collaborative model training while preserving data privacy, yet both centralized and decentralized approaches face challenges in scalability, security, and update validation. We propose ZK-HybridFL, a secure…

With the advent of delegated quantum computing as a service, verifying quantum computations is becoming a question of great importance. Existing information theoretically Secure Delegated Quantum Computing (SDQC) protocols require the…