相关论文: CHAINTRIX: A multi-pipeline LLM-augmented framewor…
Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, because data produced by one tool can be persisted and later reused as input to another tool,…
The rapid advancement of AI technologies and their accelerated adoption in software development necessitates a systematic evaluation of their environmental impact alongside functional correctness. While prior studies have examined…
Smart contracts are central to a myriad of critical blockchain applications, from financial transactions to supply chain management. However, their adoption is hindered by security vulnerabilities that can result in significant financial…
Large Language Models (LLMs), especially those accessed via APIs, have demonstrated impressive capabilities across various domains. However, users without technical expertise often turn to (untrustworthy) third-party services, such as…
Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime. This creates a safety gap in tool composition: an agent can…
Large language models (LLMs) remain acutely vulnerable to prompt injection and related jailbreak attacks; heuristic guardrails (rules, filters, LLM judges) are routinely bypassed. We present Contextual Integrity Verification (CIV), an…
Ethereum has become a widely used platform to enable secure, Blockchain-based financial and business transactions. However, many identified bugs and vulnerabilities in smart contracts have led to serious financial losses, which raises…
Recent large language models (LLMs) have demonstrated the ability to perform explicit multi-step reasoning such as chain-of-thought prompting. However, their intermediate steps often contain errors that can propagate leading to inaccurate…
The growing number of individual generating units, hybrid resources, and security constraints has significantly increased the computational burden of network-constrained unit commitment (UC), where most solution time is spent exploring…
Medical AI systems face two fundamental limitations. First, conventional vision-language models (VLMs) perform single-pass inference, yielding black-box predictions that cannot be audited or explained in clinical terms. Second, iterative…
Smart contracts - computer protocols that regulate the exchange of crypto-assets in trustless environments - have become popular with the spread of blockchain technologies. A landmark security property of smart contracts is liquidity: in a…
Cyber Threat Intelligence (CTI) reports document observations of cyber threats, synthesizing evidence about adversaries' actions and intent into actionable knowledge that informs detection, response, and defense planning. However, the…
Billions of dollars are lost every year in DeFi platforms by transactions exploiting business logic or accounting vulnerabilities. Existing defenses focus on static code analysis, public mempool screening, attacker contract detection, or…
We introduce the DeTerministic Virtual Machine (DTVM) Stack, a next-generation smart contract execution framework designed to address critical performance, determinism, and ecosystem compatibility challenges in blockchain networks. Building…
Prompt specifications for multi-agent large language model (LLM) systems carry data contracts and integration logic across many interdependent files but are rarely subjected to structured-inspection rigor. This paper reports a single-system…
Security vulnerabilities are increasingly prevalent in modern software and they are widely consequential to our society. Various approaches to defending against these vulnerabilities have been proposed, among which those leveraging deep…
Agentic applications are LLMs that iteratively invoke external tools to accomplish complex tasks. Such tool-based agents are rapidly becoming the dominant paradigm for deploying language models in production. Unlike traditional single-turn…
Sequential multi-agent systems built with large language models (LLMs) can automate complex software tasks, but they are hard to trust because errors quietly pass from one stage to the next. We study a traceable and accountable pipeline,…
Recent Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation. However, their ability to create complex visualizations for scaled and structured data remains largely unevaluated and underdeveloped. To…
Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. However, the continual learning aspect of these aligned LLMs has been largely overlooked. Existing…