Related papers: Auditing MCP Servers for Over-Privileged Tool Capa…
Formal methods for guaranteeing that a protocol satisfies a cryptographic security definition have advanced substantially, but such methods are still labor intensive and the need remains for an automated tool that can positively identify an…
With advances in decision-making and reasoning capabilities, multimodal agents show strong potential in computer application scenarios. Past evaluations have mainly assessed GUI interaction skills, while tool invocation abilities, such as…
Standard protocols such as the Model Context Protocol (MCP) that allow LLMs to connect to tools have recently boosted "agentic" AI applications, which, powered by LLMs' planning capabilities, promise to solve complex tasks with the access…
The integration of Large Language Models (LLMs) into network operations (AIOps) is hindered by two fundamental challenges: the stochastic grounding problem, where LLMs struggle to reliably parse unstructured, vendor-specific CLI output, and…
Recent advancements in privacy-preserving machine learning are paving the way to extend the benefits of ML to highly sensitive data that, until now, have been hard to utilize due to privacy concerns and regulatory constraints.…
As large language models (LLMs) are increasingly deployed in risk-sensitive applications such as real-world open-ended question answering (QA), ensuring the trustworthiness of their outputs has become critical. Existing selective conformal…
The significant increase in software production driven by automation and faster development lifecycles has resulted in a corresponding surge in software vulnerabilities. In parallel, the evolving landscape of software vulnerability…
Answering financial questions is often treated as an information retrieval problem. In practice, however, much of the relevant information is already available in curated vendor systems, especially for quantitative analysis. We study…
Despite various approaches being employed to detect vulnerabilities, the number of reported vulnerabilities shows an upward trend over the years. This suggests the problems are not caught before the code is released, which could be caused…
The variety of data in data lakes presents significant challenges for data analytics, as data scientists must simultaneously analyze multi-modal data, including structured, semi-structured, and unstructured data. While Large Language Models…
Today's AI agents are built on large language models (LLMs) equipped with tools to access and modify external environments, such as corporate file systems, API-accessible platforms and websites. AI agents offer the promise of automating…
Current Multimodal Large Language Models (MLLMs) rely on centralized architectures and often suffer from poor alignment between the input task and their fixed visual encoding modules, which limits performance on diverse and dynamic visual…
Computational data governance aims to make the enforcement of governance policies and legal obligations more efficient and reliable. Recent advances in natural language processing and agentic AI offer ways to improve how organizations share…
Access control is an important component for web services such as a cloud. Current clouds tend to design the access control mechanism together with the policy language on their own. It leads to two issues: (i) a cloud user has to learn…
Developers often build software on top of third-party libraries (Libs) to improve productivity, but these libraries may contain vulnerabilities that enable supply chain attacks. Existing tools detect vulnerable dependencies, yet developers…
Large language models (LLMs) are increasingly used to assist developers with code, yet their implementations of cryptographic functionality often contain exploitable flaws. Minor design choices (e.g., static initialization vectors or…
While fine-tuning services drive the rapid expansion of task capabilities in large language models (LLMs), they are often accompanied by the degradation and reorganization of safety-aligned representations, making models more prone to…
In this survey, we will explore the interaction between secure multiparty computation and the area of machine learning. Recent advances in secure multiparty computation (MPC) have significantly improved its applicability in the realm of…
The societal and economical consequences surrounding Big Data-driven platforms have increased the call for decentralized solutions. However, retrieving and querying data in more decentralized environments requires fundamentally different…
Model Context Protocol (MCP) is a rapidly adopted standard for defining and invoking external tools in LLM applications. The multi-layered architecture of MCP introduces new attack surfaces such as tool poisoning, in addition to traditional…