2 citations · 2 across the 4 of their papers we have counts for
5 papers
Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting
Oliver Stevanovic, Jasmin Wachter
Logic attack graphs grounded in scanner output provide explicit and auditable attack path reasoning LLM-based agents lack. Integrating symbolic frameworks such as MulVAL to contemp…
The Ethics of Autonomous AI Agents for Offensive Security
Andreas Happe, Jürgen Cito, Jasmin Wachter
LLM-driven autonomous agents are reshaping offensive security. Unlike traditional penetration-testing tooling - deterministic, narrowly scoped, and operated by trained practitioner…
Can AI Lower the Barrier to Cybersecurity? A Human-Centered Mixed-Methods Study of Novice CTF Learning
Cathrin Schachner, Jasmin Wachter
Capture-the-Flag (CTF) competitions serve as gateways into offensive cybersecurity, yet they often present steep barriers for novices due to complex toolchains and opaque workflows…
Are LLMs (Really) Ideological? An IRT-based Analysis and Alignment Tool for Perceived Socio-Economic Bias in LLMs
Jasmin Wachter, Michael Radloff, Maja Smolej +1
We introduce an Item Response Theory (IRT)-based framework to detect and quantify socioeconomic bias in large language models (LLMs) without relying on subjective human judgments.…
Graph models for Cybersecurity -- A Survey
Jasmin Wachter
Graph models are helpful means of analyzing computer networks as well as complex system architectures for security. In this paper we evaluate the current state of research for repr…