Related papers: Invisible Threats from Model Context Protocol: Gen…

Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in adversarial…

In this fast-evolving area of LLMs, our paper discusses the significant security risk presented by prompt injection attacks. It focuses on small open-sourced models, specifically the LLaMA family of models. We introduce novel defense…

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…

The flexibility and complexity of IPv6 extension headers allow attackers to create covert channels or bypass security mechanisms, leading to potential data breaches or system compromises. The mature development of machine learning has…

Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have shown that the inference performance of CLIP can be greatly…

Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP). To protect this IP, model owners typically allow user…

Recent research has explored that LLM agents are vulnerable to indirect prompt injection (IPI) attacks, where malicious tasks embedded in tool-retrieved information can redirect the agent to take unauthorized actions. Existing defenses…

Model Context Protocols (MCPs) provide a unified platform for agent systems to discover, select, and orchestrate tools across heterogeneous execution environments. As MCP-based systems scale to incorporate larger tool catalogs and multiple…

The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose…

A popular class of defenses against prompt injection attacks on large language models (LLMs) relies on fine-tuning to separate instructions and data, so that the LLM does not follow instructions that might be present with data. We evaluate…

Large Language Models (LLMs) are discovered to suffer from accurately retrieving key information. To address this, we propose Mask-Enhanced Autoregressive Prediction (MEAP), a simple yet effective training paradigm that seamlessly…

Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications such as robotics and situated conversational agents. When MLLMs reason over…

The Model Context Protocol (MCP) standardizes how AI agents discover and invoke external tools, with over 10,000 active servers and 97 million monthly SDK downloads as of early 2026. Yet MCP does not yet standardize how agents safely…

With the development of natural language processing (NLP), large language models (LLMs) are becoming increasingly popular. LLMs are integrating more into everyday life, raising public concerns about their security vulnerabilities.…

Bringing generative AI into the architecture, engineering and construction (AEC) field requires systems that can translate natural language instructions into actions on standardized data models. We present MCP4IFC, a comprehensive…

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to…

Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…