Related papers: An Empirical Evaluation of LLMs for Solving Offens…

Large language models are rapidly changing how learners acquire and demonstrate cybersecurity skills. However, when human--AI collaboration is allowed, educators still lack validated competition designs and evaluation practices that remain…

Although language model (LM) agents have demonstrated increased performance in multiple domains, including coding and web-browsing, their success in cybersecurity has been limited. We present EnIGMA, an LM agent for autonomously solving…

The extraction of a small number of relevant insights from vast amounts of data is a crucial component of data-driven decision-making. However, accomplishing this task requires considerable technical skills, domain expertise, and human…

Large language models (LLMs) are increasingly used to help security analysts manage the surge of cyber threats, automating tasks from vulnerability assessment to incident response. Yet in operational CTI workflows, reliability gaps remain…

With the rapid development of technology and the acceleration of digitalisation, the frequency and complexity of cyber security threats are increasing. Traditional cybersecurity approaches, often based on static rules and predefined…

As the frequency of cyber threats increases, conventional penetration testing is failing to capture the entirety of todays complex environments. To solve this problem, we propose the Vulnerability Mitigation System (VMS), a novel agent…

Understanding how cognitive biases influence adversarial decision-making is essential for developing effective cyber defenses. Capture-the-Flag (CTF) competitions provide an ecologically valid testbed to study attacker behavior at scale,…

This article examines the integration of IT competitions, in particular Capture The Flag, into an information systems management course to fill skills gaps, particularly in the field of cybersecurity. An educational CTF team has been set up…

This paper studies how multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We…

According to a recent survey with more than 4000 software developers, less than half of developers can spot security holes. As a result, software products present a low-security quality expressed by vulnerabilities that can be exploited by…

This paper presents a critical examination of the surprising efficacy of Large Language Models (LLMs) in penetration testing. The paper thoroughly reviews the evolution of LLMs and their rapidly expanding capabilities which render them…

Analyzing Open Source Intelligence (OSINT) from large volumes of data is critical for drafting and publishing comprehensive CTI reports. This process usually follows a three-stage workflow -- triage, deep search and TI drafting. While Large…

Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs offer cyber threat intelligence (CTI) to support vulnerability assessment and incident…

Large Language Models (LLMs) have demonstrated potential in code generation, yet they struggle with the multi-step, stateful reasoning required for offensive cybersecurity operations. Existing research often relies on static benchmarks that…

Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effectively, but miss how real Capture-the-Flag (CTF) participants…

The rapid advancement of Large Language Models (LLMs) has opened up new opportunities for leveraging artificial intelligence in a variety of application domains, including cybersecurity. As the volume and sophistication of cyber threats…

The recent progression of Large Language Models (LLMs) has witnessed great success in the fields of data-centric applications. LLMs trained on massive textual datasets showed ability to encode not only context but also ability to provide…

Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and…

Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excelling at software engineering tasks through verified feedback loops. Yet, scalable and generalizable…

In this paper, we present CTF Pilot, a GitOps-based framework for the deployment and management of Capture The Flag (CTF) competitions. By leveraging Git repositories as the single source of truth for challenge definitions and…