Related papers: MCPTox: A Benchmark for Tool Poisoning Attack on R…
The Model Context Protocol (MCP) enhances large language models (LLMs) by integrating external tools, enabling dynamic aggregation of real-time data to improve task execution. However, its non-isolated execution context introduces critical…
Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks…
During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited…
LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing…
Large language model powered autonomous agents demand robust, standardized protocols to integrate tools, share contextual data, and coordinate tasks across heterogeneous systems. Ad-hoc integrations are difficult to scale, secure, and…
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…
The AI agent ecosystem has converged on two protocols: the Model Context Protocol (MCP) for tool invocation and Agent-to-Agent (A2A) for single-principal task delegation. Both assume a single controlling principal, meaning one person or…
Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…
Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also…
Large Language Model (LLM) agents increasingly interact with external systems through tool-calling protocols such as the Model Context Protocol (MCP). In prevailing architectures, the agent must reason about every tool invocation in every…
The efficacy of availability poisoning, a method of poisoning data by injecting imperceptible perturbations to prevent its use in model training, has been a hot subject of investigation. Previous research suggested that it was difficult to…
Bioinformatics tools are essential for complex computational biology tasks, yet their integration with emerging AI-agent frameworks is hindered by incompatible interfaces, heterogeneous input-output formats, and inconsistent parameter…
Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…
Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…
Computer-use agents (CUAs) that interact with real computer systems can perform automated tasks but face critical safety risks. Ambiguous instructions may trigger harmful actions, and adversarial users can manipulate tool execution to…
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…
LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user-agent-environment interactions to achieve…
Large language models are increasingly used as orchestrators of external tools via the Model Context Protocol (MCP), but MCP is built for software services with megabytes of memory and does not descend to the microcontrollers that dominate…
Tool-using LLM agents increasingly rely on external tools to make consequential decisions, yet most existing agent-security benchmarks and defenses implicitly assume that tool feedback is trustworthy once a tool has been selected. We study…
Human-AI collaboration faces growing challenges as AI systems increasingly outperform humans on complex tasks, while humans remain responsible for orchestration, validation, and decision oversight. To address this imbalance, we introduce…