An official website of the United States government
With the growing development and deployment of large language models (LLMs) in both industrial and academic fields, their security and safety concerns have become increasingly critical. However, recent studies indicate that LLMs face numerous vulnerabilities, including data poisoning, prompt injections, and unauthorized data exposure, which conventional methods have struggled to address fully. In parallel, blockchain technology, known for its data immutability and decentralized structure, offers a promising foundation for safeguarding LLMs. In this survey, we aim to comprehensively assess how to leverage blockchain technology to enhance LLMs' security and safety. Besides, we propose a new taxonomy of blockchain for large language models (BC4LLMs) to systematically categorize related works in this emerging field. Our analysis includes novel frameworks and definitions to delineate security and safety in the context of BC4LLMs, highlighting potential research directions and challenges at this intersection.Through this study, we aim to stimulate targeted advancements in blockchain-integrated LLM security.
more »
« less
Reputation as Contextual Knowledge: Incentives and External Value in Truthful Blockchain Oracles
The primary strengths of blockchain systems come from strong guarantees of immutability and reliability, and these systems can be extended with programmatic logic through Smart Contracts. Many such programmatic use cases would benefit from the use of external data. However, the method of bringing that data onto the blockchain needs to be trustworthy and secure. Otherwise, the benefits of blockchain, namely distributed trust, no single points of failure, and immutability, would be at risk. Blockchain oracles are proposed as a conceptual solution to this problem. A blockchain oracle acts as a trusted intermediary to external data. In this work we analyze existing proposals for Discernible event oracle mechanisms, which seek to address oracle queries with a broad knowledgeable answering population, to characterize problems related to the incentives imposed by external value that depends on oracle outcomes. In doing so, we focus on continued challenges to voting based oracles, including trust limitations and the need to match questions to knowledgeable answering parties. To address these difficulties, we propose an extension to existing oracle protocols to utilize reputation as a tool to measure value and as a tool to associate questions with context. By providing a method to track contextual knowledge, our proposal allows for context-based query matching and enables higher probability of correctness for a given population size as well as stronger participation incentives.
more »
« less
- Award ID(s):
- 2113718
- PAR ID:
- 10503717
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE International Conference on Blockchain and Cryptocurrency
- ISSN:
- 2832-8906
- ISBN:
- 979-8-3503-1019-1
- Page Range / eLocation ID:
- 1 to 9
- Format(s):
- Medium: X
- Location:
- Dubai, United Arab Emirates
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Critical to answering large-scale questions in biology is the integration of knowledge from different disciplines into a coherent, computable whole. Controlled vocabularies such as ontologies represent a clear path toward this goal. Using survey questionnaires, we examined the attitudes of biologists toward adopting controlled vocabularies in phenotype publications. Our questions cover current experience and overall attitude with controlled vocabularies, the awareness of the issues around ambiguity and inconsistency in phenotype descriptions and post-publication professional data curation, the preferred solutions and the effort and desired rewards for adopting a new authoring workflow. Results suggest that although the existence of controlled vocabularies is widespread, their use is not common. A majority of respondents (74%) are frustrated with ambiguity in phenotypic descriptions, and there is a strong agreement (mean agreement score 4.21 out of 5) that author curation would better reflect the original meaning of phenotype data. Moreover, the vast majority (85%) of researchers would try a new authoring workflow if resultant data were more consistent and less ambiguous. Even more respondents (93%) suggested that they would try and possibly adopt a new authoring workflow if it required 5% additional effort as compared to normal, but higher rates resulted in a steep decline in likely adoption rates. Among the four different types of rewards, two types of citations were the most desired incentives for authors to produce computable data. Overall, our results suggest the adoption of a new authoring workflow would be accelerated by a user-friendly and efficient software-authoring tool, an increased awareness of the challenges text ambiguity creates for external curators and an elevated appreciation of the benefits of controlled vocabularies.more » « less
-
In this work, we demonstrate the design and implementation of a novel privacy-preserving blockchain for the resource-constrained Internet of Things (IoT). Blockchain, by design, ensures trust, provides built-in integrity of information and security of immutability in an IoT system without the need of a centralized entity. However, its slow transaction rate, lack of transaction privacy, and high resource consumption are three of the major hindrances to the practical realization of blockchain in IoT. While directed acyclic graphs (DAG)-based blockchain variants (e.g., hashgraph) improve the transaction rate, the other two problems remain open. To this end, we designed and constructed the prototype of a blockchain by utilizing the benefits of high transaction rate and miner-free transaction validation process from hashgraph. The proposed blockchain, coined as PrivLiteChain, implements the concept of local differential privacy to provide transaction privacy and temporal constraint to the lifecycle of the blockchain to make it lightweight.more » « less
-
Blockchain has emerged as a solution for ensuring accurate and truthful environmental variable monitoring needed for the management of pollutants and natural resources. The immutability property of blockchain helps protect the measured data on pollution and natural resources to enable truthful reporting and effective management and control of polluting agents. However, specifics on what to measure, how to use blockchain, and highlighting which blockchain frameworks have been adopted need to be explored to fill the research gaps. Therefore, we review existing works on the use of blockchain for monitoring and managing environmental variables in this paper. Specifically, we examine existing blockchain applications on greenhouse gas emissions, solid and plastic waste, food waste, food security, water usage, and the circular economy and identify what motivates the adoption of blockchain, features sought, used blockchain frameworks and consensus algorithms, and the adopted supporting technologies to complement data sensing and reporting. We conclude the review by identifying practical works that provide implementation details for rapid adoption and remaining challenges that merit future research.more » « less
-
Vincent Poor and Zhu Han (Ed.)Recently, blockchain has received much attention from the mobility-centric Internet of Things (IoT). It is deemed the key to ensuring the built-in integrity of information and security of immutability by design in the peer-to-peer network (P2P) of mobile devices. In a permissioned blockchain, the authority of the system has control over the identities of its users. Such information can allow an ill-intentioned authority to map identities with their spatiotemporal data, which undermines the location privacy of a mobile user. In this paper, we study the location privacy preservation problem in the context of permissioned blockchain-based IoT systems under three conditions. First, the authority of the blockchain holds the public and private key distribution task in the system. Second, there exists a spatiotemporal correlation between consecutive location-based transactions. Third, users communicate with each other through short-range communication technologies such that it constitutes a proof of location (PoL) on their actual locations. We show that, in a permissioned blockchain with an authority and a presence of a PoL, existing approaches cannot be applied using a plug-and-play approach to protect location privacy. In this context, we propose BlockPriv, an obfuscation technique that quantifies, both theoretically and experimentally, the relationship between privacy and utility in order to dynamically protect the privacy of sensitive locations in the permissioned blockchain.more » « less
