Search for: All records

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. 

Abstract DNA has emerged as a promising material to address growing data storage demands. We recently demonstrated a structure-based DNA data storage approach where DNA probes are spatially oriented on the surface of DNA origami and decoded using DNA-PAINT. In this approach, larger origami structures could improve the efficiency of reading and writing data. However, larger origami require long single-stranded DNA scaffolds that are not commonly available. Here, we report the engineering of a novel longer DNA scaffold designed to produce a larger rectangle origami needed to expand the origami-based digital nucleic acid memory (dNAM) approach. We confirmed that this scaffold self-assembled into the correct origami platform and correctly positioned DNA data strands using atomic force microscopy and DNA-PAINT super-resolution microscopy. This larger structure enables a 67% increase in the number of data points per origami and will support efforts to efficiently scale up origami-based dNAM. 

Abstract Deoxyribonucleic acid (DNA) is emerging as an alternative archival memory technology. Recent advancements in DNA synthesis and sequencing have both increased the capacity and decreased the cost of storing information in de novo synthesized DNA pools. In this survey, we review methods for translating digital data to and/or from DNA molecules. An emphasis is placed on methods which have been validated by storing and retrieving real-world data via in-vitro experiments. 

Abstract DNA is a compelling alternative to non-volatile information storage technologies due to its information density, stability, and energy efficiency. Previous studies have used artificially synthesized DNA to store data and automated next-generation sequencing to read it back. Here, we report digital Nucleic Acid Memory (dNAM) for applications that require a limited amount of data to have high information density, redundancy, and copy number. In dNAM, data is encoded by selecting combinations of single-stranded DNA with (1) or without (0) docking-site domains. When self-assembled with scaffold DNA, staple strands form DNA origami breadboards. Information encoded into the breadboards is read by monitoring the binding of fluorescent imager probes using DNA-PAINT super-resolution microscopy. To enhance data retention, a multi-layer error correction scheme that combines fountain and bi-level parity codes is used. As a prototype, fifteen origami encoded with ‘Data is in our DNA!\n’ are analyzed. Each origami encodes unique data-droplet, index, orientation, and error-correction information. The error-correction algorithms fully recover the message when individual docking sites, or entire origami, are missing. Unlike other approaches to DNA-based data storage, reading dNAM does not require sequencing. As such, it offers an additional path to explore the advantages and disadvantages of DNA as an emerging memory material.