Related papers: CapSeal: Capability-Sealed Secret Mediation for Se…
The increasing complexity and scale of modern digital environments have exposed significant gaps in traditional cybersecurity penetration testing methods, which are often time-consuming, labor-intensive, and unable to rapidly adapt to…
In the vast domain of cybersecurity, the transition from reactive defense to offensive has become critical in protecting digital infrastructures. This paper explores the integration of Artificial Intelligence (AI) into offensive…
While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…
A multi-agent pipeline with N agents typically issues N LLM calls per run. Merging agents into fewer calls (compound execution) promises token savings, but naively merged calls silently degrade quality through tool loss and prompt…
Recent capability increases in large language models (LLMs) open up applications in which groups of communicating generative AI agents solve joint tasks. This poses privacy and security challenges concerning the unauthorised sharing of…
Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly…
Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust and communication…
The Model Context Protocol (MCP), introduced by Anthropic in November 2024 and now governed by the Linux Foundation's Agentic AI Foundation, has rapidly become the de facto standard for connecting large language model (LLM)-based agents to…
Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…
A fundamental limitation of current LLM-based AI agents is their inability to build differentiated trust among each other at the onset of an agent-to-agent dialogue. However, autonomous and interoperable trust establishment becomes…
The gossip-based distributed algorithms are widely used to solve decentralized optimization problems in various multi-agent applications, while they are generally vulnerable to data injection attacks by internal malicious agents as each…
AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…
This paper systematically investigates the security, privacy, and ethical risks, as well as the traceability challenges of OpenClaw, a locally executable AI agent system for natural language interaction and real-world task completion. While…
Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, reasoning, and question answering. However, training such…
Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that failures stem from both tool-use accuracy (how well an agent invokes a tool) and intrinsic…
As the "agentic web" takes shape-billions of AI agents (often LLM-powered) autonomously transacting and collaborating-trust shifts from human oversight to protocol design. In 2025, several inter-agent protocols crystallized this shift,…
Honeypots are deception systems that emulate vulnerable services to collect threat intelligence. While deploying many honeypots increases the opportunity to observe attacker behaviour, in practise network and computational resources limit…
Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…
AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify…
As Agentic AI systems evolve from basic workflows to complex multi agent collaboration, robust protocols such as Google's Agent2Agent (A2A) become essential enablers. To foster secure adoption and ensure the reliability of these complex…