Trust the Process: Zero-Knowledge Machine Learning to Enhance Trust in Generative AI Interactions

• URL: http://arxiv.org/abs/2402.06414v1
• Date: Fri, 9 Feb 2024 14:00:16 GMT
• Title: Trust the Process: Zero-Knowledge Machine Learning to Enhance Trust in Generative AI Interactions
• Authors: Bianca-Mihaela Ganescu, Jonathan Passerat-Palmbach
• Abstract summary: It explores using cryptographic techniques, particularly Zero-Knowledge Proofs (ZKPs), to address concerns regarding performance fairness and accuracy. Applying ZKPs to Machine Learning models, known as ZKML (Zero-Knowledge Machine Learning), enables independent validation of AI-generated content. We introduce snarkGPT, a practical ZKML implementation for transformers, to empower users to verify output accuracy and quality while preserving model privacy.
• Score: 1.3688201404977818
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Generative AI, exemplified by models like transformers, has opened up new possibilities in various domains but also raised concerns about fairness, transparency and reliability, especially in fields like medicine and law. This paper emphasizes the urgency of ensuring fairness and quality in these domains through generative AI. It explores using cryptographic techniques, particularly Zero-Knowledge Proofs (ZKPs), to address concerns regarding performance fairness and accuracy while protecting model privacy. Applying ZKPs to Machine Learning models, known as ZKML (Zero-Knowledge Machine Learning), enables independent validation of AI-generated content without revealing sensitive model information, promoting transparency and trust. ZKML enhances AI fairness by providing cryptographic audit trails for model predictions and ensuring uniform performance across users. We introduce snarkGPT, a practical ZKML implementation for transformers, to empower users to verify output accuracy and quality while preserving model privacy. We present a series of empirical results studying snarkGPT's scalability and performance to assess the feasibility and challenges of adopting a ZKML-powered approach to capture quality and performance fairness problems in generative AI models.

Related papers

• Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning [53.398270878295754]
  Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs)<n>We suggest categorizing tokens within each corpus into two parts -- positive and negative tokens -- based on whether they are useful to improve model performance.<n>We conduct experiments on well-established benchmarks, finding that this forgetting mechanism not only improves overall model performance and also facilitate more diverse model responses.
  arXiv  Detail & Related papers  (2025-08-06T11:22:23Z)
• LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration [0.0]
  Large Language Models (LLMs) have demonstrated impressive performance across various tasks.<n>We propose LENS (Learning ENsemble confidence from Neural States), a novel approach that learns to estimate model confidence by analyzing internal representations.
  arXiv  Detail & Related papers  (2025-07-31T00:35:45Z)
• White-Basilisk: A Hybrid Model for Code Vulnerability Detection [50.49233187721795]
  We introduce White-Basilisk, a novel approach to vulnerability detection that demonstrates superior performance.<n>White-Basilisk achieves results in vulnerability detection tasks with a parameter count of only 200M.<n>This research establishes new benchmarks in code security and provides empirical evidence that compact, efficiently designed models can outperform larger counterparts in specialized tasks.
  arXiv  Detail & Related papers  (2025-07-11T12:39:25Z)
• Engineering Trustworthy Machine-Learning Operations with Zero-Knowledge Proofs [1.7723990552388873]
  Zero-Knowledge Proofs (ZKPs) offer a cryptographic solution that enables provers to demonstrate, through verified computations, adherence to set requirements without revealing sensitive model details or data.<n>We identify five key properties (non-interactivity, transparent setup, standard representations, succinctness, and post-quantum security) critical for their application in AI validation and verification pipelines.
  arXiv  Detail & Related papers  (2025-05-26T15:39:11Z)
• Financial Fraud Detection Using Explainable AI and Stacking Ensemble Methods [0.6642919568083927]
  We propose a fraud detection framework that combines a stacking ensemble of gradient boosting models: XGBoost, LightGBM, and CatBoost.<n>XAI techniques are used to enhance the transparency and interpretability of the model's decisions.
  arXiv  Detail & Related papers  (2025-05-15T07:53:02Z)
• Enhancing Trust in AI Marketplaces: Evaluating On-Chain Verification of Personalized AI models using zk-SNARKs [8.458944388986067]
  This paper addresses the challenge of verifying personalized AI models in decentralized environments. We propose a novel framework that integrates zero-knowledge succinct non-interactive arguments of knowledge (zk-SNARKs) with Chainlink decentralized oracles. Our results indicate the framework's efficacy, with key metrics including proof generation taking an average of 233.63 seconds and verification time of 61.50 seconds.
  arXiv  Detail & Related papers  (2025-04-07T07:38:29Z)
• Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling [48.15636223774418]
  Large language models (LLMs) frequently hallucinate due to misaligned self-awareness. Existing approaches mitigate hallucinations via uncertainty estimation or query rejection. We propose the Explicit Knowledge Boundary Modeling framework to integrate fast and slow reasoning systems.
  arXiv  Detail & Related papers  (2025-03-04T03:16:02Z)
• KBAlign: Efficient Self Adaptation on Specific Knowledge Bases [73.34893326181046]
  We present KBAlign, a self-supervised framework that enhances RAG systems through efficient model adaptation.<n>Our key insight is to leverage the model's intrinsic capabilities for knowledge alignment through two innovative mechanisms.<n> Experiments demonstrate that KBAlign can achieve 90% of the performance gain obtained through GPT-4-supervised adaptation.
  arXiv  Detail & Related papers  (2024-11-22T08:21:03Z)
• Verifying Machine Unlearning with Explainable AI [46.7583989202789]
  We investigate the effectiveness of Explainable AI (XAI) in verifying Machine Unlearning (MU) within context of harbor front monitoring. Our proof-of-concept introduces attribution feature as an innovative verification step for MU, expanding beyond traditional metrics. We propose two novel XAI-based metrics, Heatmap Coverage (HC) and Attention Shift (AS) to evaluate the effectiveness of these methods.
  arXiv  Detail & Related papers  (2024-11-20T13:57:32Z)
• Design of reliable technology valuation model with calibrated machine learning of patent indicators [14.31250748501038]
  We propose an analytical framework for reliable technology valuation using calibrated ML models. We extract quantitative patent indicators that represent various technology characteristics as input data.
  arXiv  Detail & Related papers  (2024-06-08T11:52:37Z)
• LaPLACE: Probabilistic Local Model-Agnostic Causal Explanations [1.0370398945228227]
  We introduce LaPLACE-explainer, designed to provide probabilistic cause-and-effect explanations for machine learning models. The LaPLACE-Explainer component leverages the concept of a Markov blanket to establish statistical boundaries between relevant and non-relevant features. Our approach offers causal explanations and outperforms LIME and SHAP in terms of local accuracy and consistency of explained features.
  arXiv  Detail & Related papers  (2023-10-01T04:09:59Z)
• Federated Learning-Empowered AI-Generated Content in Wireless Networks [58.48381827268331]
  Federated learning (FL) can be leveraged to improve learning efficiency and achieve privacy protection for AIGC. We present FL-based techniques for empowering AIGC, and aim to enable users to generate diverse, personalized, and high-quality content.
  arXiv  Detail & Related papers  (2023-07-14T04:13:11Z)
• Evaluating Explainability in Machine Learning Predictions through Explainer-Agnostic Metrics [0.0]
  We develop six distinct model-agnostic metrics designed to quantify the extent to which model predictions can be explained. These metrics measure different aspects of model explainability, ranging from local importance, global importance, and surrogate predictions. We demonstrate the practical utility of these metrics on classification and regression tasks, and integrate these metrics into an existing Python package for public use.
  arXiv  Detail & Related papers  (2023-02-23T15:28:36Z)
• Information Theoretic Evaluation of Privacy-Leakage, Interpretability, and Transferability for a Novel Trustworthy AI Framework [11.764605963190817]
  Guidelines and principles of trustworthy AI should be adhered to in practice during the development of AI systems. This work suggests a novel information theoretic trustworthy AI framework based on the hypothesis that information theory enables taking into account the ethical AI principles.
  arXiv  Detail & Related papers  (2021-06-06T09:47:06Z)
• Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design [76.29738151117583]
  Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients. However, low quality models could be uploaded to the aggregator server by unreliable clients, leading to a degradation or even a collapse of training. We model these unreliable behaviors of clients and propose a defensive mechanism to mitigate such a security risk.
  arXiv  Detail & Related papers  (2021-05-10T08:02:27Z)
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty [66.17147341354577]
  We argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. We describe how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness.
  arXiv  Detail & Related papers  (2020-11-15T17:26:14Z)
• Trustworthy AI [75.99046162669997]
  Brittleness to minor adversarial changes in the input data, ability to explain the decisions, address the bias in their training data, are some of the most prominent limitations. We propose the tutorial on Trustworthy AI to address six critical issues in enhancing user and public trust in AI systems.
  arXiv  Detail & Related papers  (2020-11-02T20:04:18Z)
• Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources [78.72922528736011]
  We propose a novel approach, black-box adversarial reprogramming (BAR), that repurposes a well-trained black-box machine learning model. Using zeroth order optimization and multi-label mapping techniques, BAR can reprogram a black-box ML model solely based on its input-output responses. BAR outperforms state-of-the-art methods and yields comparable performance to the vanilla adversarial reprogramming method.
  arXiv  Detail & Related papers  (2020-07-17T01:52:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.