arXiv subjects

Alireza Arbabi

Publications and source records attributed to Alireza Arbabi.

4 recordsLinked to original sources

arXiv2026

Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard

Large language models (LLMs) are increasingly released and deployed through opaque development and deployment pipelines, enabling model providers to inject intentional, provider-specific policies without officially announcing them. As a result, various models have been reported to generate responses reflecting proprietary rules and organizational interests, leading to censorship or misinformation on controversial topics. However, systematic identification of such alignment remains a fundamental challenge, complicated by the ambiguity of what ``proprietary'' entails in different contexts. In this paper, we propose a statistical framework for detecting proprietary alignment in black-box language models via comparative behavioral analysis. Our approach quantifies systematic deviations between the responses of a target model and those of a reference set of baseline models in a shared semantic space. By evaluating relative behavioral divergence rather than absolute correctness, our framework enables principled auditing under black-box access. Applied to several widely discussed but previously unquantified cases, it provides a systematic and scalable basis for external assessment of provider-specific alignment behavior in large language models.

cs.CL↗

arXiv2025

Relative Bias: A Comparative Framework for Quantifying Bias in LLMs

The growing deployment of large language models (LLMs) has amplified concerns regarding their inherent biases, raising critical questions about their fairness, safety, and societal impact. However, quantifying LLM bias remains a fundamental challenge, complicated by the ambiguity of what "bias" entails. This challenge grows as new models emerge rapidly and gain widespread use, while introducing potential biases that have not been systematically assessed. In this paper, we propose the Relative Bias framework, a method designed to assess how an LLM's behavior deviates from other LLMs within a specified target domain. We introduce two complementary methodologies: (1) Embedding Transformation analysis, which captures relative bias patterns through sentence representations over the embedding space, and (2) LLM-as-a-Judge, which employs a language model to evaluate outputs comparatively. Applying our framework to several case studies on bias and alignment scenarios following by statistical tests for validation, we find strong alignment between the two scoring methods, offering a systematic, scalable, and statistically grounded approach for comparative bias analysis in LLMs.

cs.CL↗

arXiv2023

Mixing Solutions in Bitcoin and Ethereum Ecosystems: A Review and Tutorial

This manuscript presents an exhaustive review of blockchain-based mixing services, aiming to fill the existing gap between academic innovations and real-world implementations. Starting with an identification of the core functionalities and techniques employed by mixing services, the paper delves into detailed explanations of these operational mechanisms. It further outlines an evaluation framework tailored for a rigorous assessment, highlighting the key vulnerabilities and strengths of various solutions. In addition, the study identifies potential attack vectors that compromise these services. The paper explores the dual nature of mixing services, while they contribute to the preservation of privacy, a cornerstone of blockchain technologies, they can also facilitate illicit activities. By addressing key research questions, this study not only offers a comprehensive overview of the current state of mixing services but also sets the stage for future academic discourse in this evolving field.

cs.CR↗

arXiv2022

RPoA: Redefined Proof of Activity

The consensus protocol is the core of a blockchain system which guarantees its secure and stable operation. Proof of Activity (PoA) is a consensus protocol that tries to address some of the issues pertinent to the most widely used protocols, such as Proof of Stake (PoS) and Proof of Work (PoW). However, it still needs to solve the issues regarding high energy consumption, significant resources required, high mining latency, and the need for private blockchains. In this paper, we propose Redefined Proof of Activity (RPoA), a new consensus protocol that builds on top of some of the best features of the existing protocols, such as PoW, PoS, and PoA, and values active service provided by users on the network. Our approach tries to address the issues above and falls in the service-based protocols category that gives mining credit to users as they serve on the network.

cs.CR↗