Related papers: ZKTorch: Compiling ML Inference to Zero-Knowledge …

Zero-knowledge rollups rely on provers to generate multi-step state transition proofs under strict finality and availability constraints. These steps require expensive hardware (e.g., GPUs), and finality is reached only once all stages…

Pre-trained machine learning (ML) predictions have been increasingly used to complement incomplete data to enable downstream scientific inquiries, but their naive integration risks biased inferences. Recently, multiple methods have been…

Training contemporary AI models requires investment in procuring learning data and computing resources, making the models intellectual property of the owners. Popular model watermarking solutions rely on key input triggers for detection;…

We introduce a technology to formally verify that a software system satisfies a temporal specification of functional correctness, without revealing the system itself. Our method combines a deductive approach to model checking to obtain a…

Privacy concerns in machine learning systems have grown significantly with the increasing reliance on sensitive user data for training large-scale models. This paper introduces a novel framework combining Probably Approximately Correct…

With the growing concern of AI safety, there is a need to trust the computations done by machine learning (ML) models. Blockchain technology, known for recording data and running computations transparently and in a tamper-proof manner, can…

As society grows more reliant on machine learning, ensuring the security of machine learning systems against sophisticated attacks becomes a pressing concern. A recent result of Goldwasser, Kim, Vaikuntanathan, and Zamir (2022) shows that…

Federated Learning (FL) has emerged as a promising paradigm in distributed machine learning, enabling collaborative model training while preserving data privacy. However, despite its many advantages, FL still contends with significant…

We propose a middleware solution designed to facilitate seamless integration of privacy using zero-knowledge proofs within various multi-chain protocols, encompassing domains such as DeFi, gaming, social networks, DAOs, e-commerce, and the…

Zero-knowledge proofs (ZKPs) are central to secure and privacy-preserving computation, with zk-SNARKs and zk-STARKs emerging as leading frameworks offering distinct trade-offs in efficiency, scalability, and trust assumptions. While their…

In principle, explanations are intended as a way to increase trust in machine learning models and are often obligated by regulations. However, many circumstances where these are demanded are adversarial in nature, meaning the involved…

Neural models combining representation learning and reasoning in an end-to-end trainable manner are receiving increasing interest. However, their use is severely limited by their computational complexity, which renders them unusable on real…

Resource limitations often constrain the parameter counts of Large Language Models (LLMs), hindering their performance. While existing methods employ parameter sharing to reuse the same parameter set under fixed budgets, such approaches…

In this paper, we present VerifyML, the first secure inference framework to check the fairness degree of a given Machine learning (ML) model. VerifyML is generic and is immune to any obstruction by the malicious model holder during the…

Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capabilities. This problem is further exacerbated by malicious…

Zero-knowledge proofs (ZKPs) are the cornerstone of programmable cryptography. They enable (1) privacy-preserving and verifiable computation across blockchains, and (2) an expanding range of off-chain applications such as credential…

Gradient boosted decision trees, particularly XGBoost, are among the most effective methods for tabular data. As deployment in sensitive settings increases, cryptographic guarantees of model integrity become essential. We present ZKBoost,…

This study proposes a lightweight Zero-Knowledge authentication model supported by QR codes. The approach is based on the Schnorr authentication protocol and provides an additional security layer against replay attacks through nonce and…

MPC-in-the-Head (MitH) is a general framework that allows constructing efficient Zero Knowledge protocols for general NP-relations from secure multiparty computation (MPC) protocols. In this paper we give the first machine-checked…

Numerous theorems, such as those in geometry, are often presented in multimodal forms (e.g., diagrams). Humans benefit from visual reasoning in such settings, using diagrams to gain intuition and guide the proof process. Modern Multimodal…