Related papers: zkFinGPT: Zero-Knowledge Proofs for Financial Gene…

With recent advances in large language models (LLMs), this paper explores the potential of leveraging state-of-the-art LLMs,such as GPT-4, to transfer existing human-written properties (e.g.,those from Certora auditing reports) and…

Vision Transformers (ViTs) have demonstrated superior performance over Convolutional Neural Networks (CNNs) in various vision-related tasks such as classification, object detection, and segmentation due to their use of self-attention…

This paper presents a new method for quantum identity authentication (QIA) protocols. The logic of classical zero-knowledge proofs (ZKPs) due to Schnorr is applied in quantum circuits and algorithms. This novel approach gives an exact way…

Financial AI systems must produce answers grounded in specific regulatory filings, yet current LLMs fabricate metrics, invent citations, and miscalculate derived quantities. These errors carry direct regulatory consequences as the EU AI…

Zero-inflated datasets, which have an excess of zero outputs, are commonly encountered in problems such as climate or rare event modelling. Conventional machine learning approaches tend to overestimate the non-zeros leading to poor…

The challenge of formal proof generation has a rich history, but with modern techniques, we may finally be at the stage of making actual progress in real-life mathematical problems. This paper explores the integration of ChatGPT and basic…

Machine Learning models require a vast amount of data for accurate training. In reality, most data is scattered across different organizations and cannot be easily integrated under many legal and practical constraints. Federated Transfer…

Verifying that a compiled binary originates from its claimed source code is a fundamental security requirement, called source code provenance. Achieving verifiable source code provenance in practice remains challenging. The most popular…

Federated Learning (FL) enables collaborative training of medical AI models across hospitals without centralizing patient data. However, the exchange of model updates exposes critical vulnerabilities: gradient inversion attacks can…

Large language models (LLMs) are rapidly being adopted across various domains. However, their adoption in banking industry faces resistance due to demands for high accuracy, regulatory compliance, and the need for verifiable and grounded…

The instantaneous quantum polynomial time model (or the IQP model) is one of promising models to demonstrate a quantum computational advantage over classical computers. If the IQP model can be efficiently simulated by a classical computer,…

BANZKP is the best to date Zero Knowledge Proof (ZKP) based secure lightweight and energy efficient authentication scheme designed for Wireless Area Network (WBAN). It is vulnerable to several security attacks such as the replay attack,…

Zero-knowledge and multi-prover systems are both central notions in classical and quantum complexity theory. There is, however, little research in quantum multi-prover zero-knowledge systems. This paper studies complexity-theoretical…

Leveraging large language models (LLMs) to generate high-stakes documents, such as informed consent forms (ICFs), remains a significant challenge due to the extreme need for regulatory compliance and factual accuracy. Here, we present…

Large language models such as Open AI's Generative Pre-trained Transformer (GPT) models are proficient at answering questions, but their knowledge is confined to the information present in their training data. This limitation renders them…

The breakthrough performance of large language models (LLMs) comes with major computational footprints and high deployment costs. In this paper, we progress towards resolving this problem by proposing a novel structured compression approach…

Tax returns contain key financial information of interest to third parties: public officials are asked to share financial data for transparency, companies seek to assess the financial status of business partners, and individuals need to…

Node classification is a fundamental problem in information retrieval with many real-world applications, such as community detection in social networks, grouping articles published online and product categorization in e-commerce. Zero-shot…

Training large language models (LLMs) is resource-intensive and expensive, making protecting intellectual property (IP) for LLMs crucial. Recently, embedding fingerprints into LLMs has emerged as a prevalent method for establishing model…

We introduce a novel framework named ClarifyGPT, which aims to enhance code generation by empowering LLMs with the ability to identify ambiguous requirements and ask targeted clarifying questions. In particular, ClarifyGPT first detects…