相关论文: Verifiable evaluations of machine learning models …

The opaque nature of transformer-based models, particularly in applications susceptible to unethical practices such as dark-patterns in user interfaces, requires models that integrate uncertainty quantification to enhance trust in…

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…

A major requirement for credit scoring models is to provide a maximally accurate risk prediction. Additionally, regulators demand these models to be transparent and auditable. Thus, in credit scoring, very simple predictive models such as…

We present VeriX (Verified eXplainability), a system for producing optimal robust explanations and generating counterfactuals along decision boundaries of machine learning models. We build such explanations and counterfactuals iteratively…

This survey provides a comprehensive examination of verifiable computing, tracing its evolution from foundational complexity theory to modern zero-knowledge succinct non-interactive arguments of knowledge (ZK-SNARKs). We explore key…

Zero-knowledge proofs (ZKPs) have evolved from being a theoretical concept providing privacy and verifiability to having practical, real-world implementations, with SNARKs (Succinct Non-Interactive Argument of Knowledge) emerging as one of…

The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. Despite the reputation of learned NN models to behave as black boxes and…

Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…

The last decade has sparked several valiant efforts in deductive verification of distributed agreement protocols such as consensus and leader election. Oddly, there have been far fewer verification efforts that go beyond the core protocols…

Zero-knowledge proof (ZKP) frameworks have the potential to revolutionize the handling of sensitive data in various domains. However, deploying ZKP frameworks with real-world data presents several challenges, including scalability,…

Machine learning techniques often lack formal correctness guarantees, evidenced by the widespread adversarial examples that plague most deep-learning applications. This lack of formal guarantees resulted in several research efforts that aim…

We consider the problem of whether a given decision model, working with structured data, has individual fairness. Following the work of Dwork, a model is individually biased (or unfair) if there is a pair of valid inputs which are close to…

The field of machine learning has seen tremendous progress in recent years, with deep learning models delivering exceptional performance across a range of tasks. However, these models often come at the cost of interpretability, as they…

A zk-SNARK is a protocol that lets one party, the prover, prove to another party, the verifier, that a statement about some privately-held information is true without revealing the information itself. This paper describes technical…

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…

Rigorous and reproducible evaluation is critical for assessing the state of the art and for guiding scientific advances in Artificial Intelligence. Evaluation is challenging in practice due to several reasons, including benchmark…

Deep Neural Networks (DNN) are crucial in approximating nonlinear functions across diverse applications, ranging from image classification to control. Verifying specific input-output properties can be a highly challenging task due to the…

Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness,…

Large language models are often adapted through parameter efficient fine tuning, but current release practices provide weak assurances about what data were used and how updates were computed. We present Verifiable Fine Tuning, a protocol…

Predictive benchmarking, the evaluation of machine learning models based on predictive performance and competitive ranking, is a central epistemic practice in machine learning research and an increasingly prominent method for scientific…