相关论文: Hyperion: Unveiling DApp Inconsistencies using LLM…
Model Context Protocol (MCP) servers contain a collection of thousands of open-source standardized tools, linking LLMs to external systems; however, existing datasets and benchmarks lack realistic, human-like user queries, remaining a…
Blockchain technology has attracted tremendous attention in both academia and capital market. However, overwhelming speculations on thousands of available cryptocurrencies and numerous initial coin offering (ICO) scams have also brought…
Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to improve their efficiency, enabling them to reach high…
Large language models (LLMs), pre-trained or fine-tuned on large code corpora, have shown effectiveness in generating code completions. However, in LLM-based code completion, LLMs may struggle to use correct and up-to-date Application…
AI agents that execute tasks via tool calls frequently hallucinate results - fabricating tool executions, misstating output counts, or presenting inferences as facts. Recent approaches to verifiable AI inference rely on zero-knowledge…
Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation, debugging, and automated reasoning. Although large language…
The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but may fail to perform well in the real world. We introduce…
This work presents the design and implementation of a decentralized application (DApp) that aims to guarantee the privacy of data related to the health area, which are stored and shared within a blockchain network. For this, encryption with…
Mini-app is an emerging form of mobile application that combines web technology with native capabilities. Its features, e.g., no need to download and no installation, have made it popular rapidly. However, privacy issues that violate the…
The rapid advancement of large language models (LLMs) demands increasingly reliable evaluation, yet current centralized evaluation suffers from opacity, overfitting, and hardware-induced variance. Our empirical analysis reveals an alarming…
Concise and meaningful method names are crucial for program comprehension and maintenance. However, method names may become inconsistent with their corresponding implementations, causing confusion and errors. Several deep learning…
A variety of mobile devices and applications have spread the usability of blockchain solutions to over 5.27 billion unique mobile phone users. The rising of Bitcoin price up to USD 50,000 in March 2021 has made many blockchain mobile…
With the rise of cryptocurrencies, many new applications built on decentralized blockchains have emerged. Blockchains are full-stack distributed systems where multiple sub-systems interact. While many deployed blockchains and decentralized…
Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a percentage point. At the same time, the computational cost of evaluating modern LLMs has…
The permission mechanism in the Android Framework is integral to safeguarding the privacy of users by managing users' and processes' access to sensitive resources and operations. As such, developers need to be equipped with an in-depth…
Mobile apps offer significant benefits, but their privacy protections often remain ineffective and confusing for users. While prior work mainly analyzes app privacy vulnerabilities, few approaches help users understand, set, and enforce…
Large Language Models for code generation frequently produce hallucinations in Fill-in-the-Middle (FIM) tasks -- plausible but incorrect completions such as invented API methods, invalid parameters, undefined variables, or non-existent…
Large language models (LLMs) showcase many desirable traits for intelligent and helpful robots. However, they are also known to hallucinate predictions. This issue is exacerbated in robotics where LLM hallucinations may result in robots…
The Smart Contract Weakness Classification Registry (SWC Registry) is a widely recognized list of smart contract weaknesses specific to the Ethereum platform. Despite the SWC Registry not being updated with new entries since 2020, the…
Real-world enterprise data intelligence workflows encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into decision-oriented insights. We introduce DAComp, a benchmark…