Related papers: Cochise: A Reference Harness for Autonomous Penetr…

Always-on AI agents (OpenClaw, Hermes Agent) run as a single persistent process under the owner's identity, folding messaging, memory, self-authored skills, scheduling, and shell into one authority boundary. This configuration opens what we…

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…

Secure inference enables privacy-preserving machine learning by leveraging cryptographic protocols that support computations on sensitive user data without exposing it. However, integrating cryptographic protocols with large language models…

By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due…

Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…

As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level…

While penetration testing plays a vital role in cybersecurity, achieving fully automated, hands-off-the-keyboard execution remains a significant research challenge. In this paper, we introduce the "Planner-Executor-Perceptor (PEP)" design…

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

Penetration testing (or pentesting) is one of the widely used and important methodologies to assess the security of computer systems and networks. Traditional pentesting relies on the domain expert knowledge and requires considerable human…

Power and cost constraints in the internet-of-things (IoT) extreme-edge and TinyML domains, coupled with increasing performance requirements, motivate a trend toward heterogeneous architectures. These designs use energy-efficient…

Production LLM coding agents drift over long sessions: they forget user-specified constraints, slip into mistakes the user already flagged, and confabulate prior agreements. White-box approaches such as persona vectors require model weights…

Creating attack paths for cyber defence exercises requires substantial expert effort. Existing automation requires vulnerability graphs or exploit sets curated in advance, limiting where it can be applied. We present AEGIS, a system that…

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound…

Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state implicit and making…

The expansion of edge computing has increased the attack surface, creating an urgent need for robust, real-time machine learning (ML)-based host intrusion detection systems (HIDS) that balance accuracy and efficiency. In such settings,…

We present a production-optimized multi-agent system designed to translate natural language queries into executable Python code for structured data analytics. Unlike systems that rely on expensive frontier models, our approach achieves high…

Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided self-refinement…

Attestation means providing evidence that a remote target system is worthy of trust for some sensitive interaction. Although attestation is already used in network access control, security management, and trusted execution environments, it…

Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic workloads induce a temporal shift from single-turn inference to multi-turn LLM-tool loops,…

Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…