Research
Research
Research
Research
8,205+ open-access research outputs.
Maximal Extractable Value (MEV) represents billions of dollars in extracted value that fundamentally shapes blockchain network dynamics and participant incentives. While research has focused on MEV ex…
Although precise recall is a core objective in Retrieval-Augmented Generation (RAG), a critical oversight persists in the field: improvements in retrieval performance do not consistently translate to …
We give a self-contained, modern exposition of \'Edouard Goursat's 1887 theorem on pseudo-elliptic integrals -- those integrals of the form $\int F(t)\,\d t/\sqrt{R(t)}$ with $R$ a cubic or quartic po…
Cross-chain NFT migration refers to the process of transferring digital assets along with their associated functionalities and guarantees between distinct blockchain platforms. However, architectural …
Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version…
AI systems rest on software with low integrity mechanisms, leaving AI systems exposed across every stage from data acquisition to final inference. This paper makes the AI supply chain a first-class ob…
We develop a geometric and information-theoretic framework for encoder-decoder learning built on the Information Bottleneck (IB) principle. Recasting IB as a rate-distortion problem with Kullback-Leib…
Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed as a privacy bounda…
As large language models are integrated into autonomous robotic systems for task planning and control, compromised inputs or unsafe model outputs can propagate through the planning pipeline to physica…
LLM agents are known to deviate from Nash equilibria in strategic interactions, but nobody has looked inside the model to understand why, or asked whether the deviation can be reversed. We do both. …
Recent research has demonstrated the potential of Large Language Models (LLMs) for autonomous penetration testing, particularly when using cloud-based restricted-weight models. However, reliance on su…
This paper explores the effectiveness of modular randomized testing for object oriented programs in Java. Modular testing involves testing individual components of a program in isolation. Often times,…
We study exact fixed-cardinality Solow--Polasky diversity subset selection on ordered finite $\ell_1$ sets, with monotone biobjective Pareto fronts and their higher-dimensional staircase analogues as …
FlyClient is a lightweight blockchain verification protocol that enables proof-of-work validation using minimal data, making it ideal for resource-constrained environments like mobile wallets, Interne…
Training trustworthy agentic LLMs requires data that shows the grounded reasoning process, not just the final answer. Existing datasets fall short: question-answering data is outcome-only, chain-of-th…
Large reasoning models such as DeepSeek-R1 and OpenAI o1 generate extended chains of thought spanning thousands of tokens, yet their integration with retrieval-augmented generation (RAG) remains funda…
Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection method…
Function-correcting codes with data protection simultaneously protect both the data and a function of the data at distinct error-correction levels. When the function receives strictly stronger protect…
Developers and organizations are using Large Language Models (LLMs) to generate security-critical code more frequently than ever, including cryptographic solutions for their products. This study prese…
The remarkable text understanding and generation capabilities of large language models (LLMs) have revitalized the field of general recommendation based on implicit user feedback. Rather than deployin…
Free open-access publishing with Google Scholar indexing.
Submission Guide →