arXiv subjects

Jasmin Wachter

Publications and source records attributed to Jasmin Wachter.

7 recordsLinked to original sources

arXiv2026

Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting

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 contemporary security workflows or agentic pipelines, however, requires translating scanner evidence to initial facts, and creating domain-specific rules. We present a semi-automated pipeline that addresses this interoperability problem and depict its feasibility in a web-security case study. Our pipeline parses findings from Trivy, Semgrep, and Nmap into MulVAL predicates and uses an LLM-assisted process to construct domain-specific Datalog rules linking scanner-detectable evidence to attack techniques. MulVAL/XSB then performs symbolic inference to generate structured attack paths. We evaluate the attack-graph construction infrastructure on 54 web Capture-the-Flag tasks from CyBench within an agentic pipeline (Hybrid Reasoner); we do not evaluate the performance of the downstream agent. Every task produced at least one goal-reaching graph, and we achieve mean ground-truth vulnerability coverage of 53.7%, with 51.9% achieving full coverage; mean noise-path rate was 83.9%. With median end-to-end time of 24.9 s (MulVAL reasoning: 2.7 s) the pipeline is feasible and runtime-practical for agentic workflows, but predicate coverage, rule coverage, and path precision remain limiting factors. Next steps include semantic rule validation and agent-level comparison for graph-guided pentesting.

cs.CR↗

arXiv2026

The Ethics of Autonomous AI Agents for Offensive Security

LLM-driven autonomous agents are reshaping offensive security. Unlike traditional penetration-testing tooling - deterministic, narrowly scoped, and operated by trained practitioners - agentic security tools exhibit indeterminacy along three independent dimensions. First, their actions are drawn from a non-deterministic policy whose outputs resist both ex-ante and ex-post explanation. This complicates incident attribution and pre-deployment safety reviews. Second, their impact is open-ended due to their non-deterministic actions, agency of utilized models, and opaque LLM supply-chains. Third, their user population is indeterminate in both size and required skill: the operating skill floor for using or developing offensive capabilities has dropped sharply. These three properties are linked thematically, but are not derivable from one another. Combined with the structural cost asymmetry between offense and defense, they enable the industrialization of offensive capability. The net short-term effect favors attackers, even if the same technology may, in the long run, democratize access to defensive practice. Existing dual-use cybersecurity and AI-ethics frameworks struggle to address this combination. Our work analyzes how moral attribution becomes diffuse between users, tool-makers, and third parties when employing autonomous AI agents for offensive security. We also examine the stakeholder impact of this technology and provide stratified recommendations.

cs.CR↗

arXiv2026

Can AI Lower the Barrier to Cybersecurity? A Human-Centered Mixed-Methods Study of Novice CTF Learning

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. Recently, agentic AI frameworks for cybersecurity promise to lower these barriers by automating and coordinating penetration testing tasks. However, their role in shaping novice learning remains underexplored. We present a human-centered, mixed-methods case study examining how agentic AI frameworks -- here Cybersecurity AI (CAI) -- mediates novice entry into CTF-based penetration testing. An undergraduate student without prior hacking experience attempted to approach performance benchmarks from a national cybersecurity challenge using CAI. Quantitative performance metrics were complemented by structured reflective analysis of learning progression and AI interaction patterns. Our thematic analysis suggest that agentic AI reduces initial entry barriers by providing overview, structure and guidance, thereby lowering the cognitive workload during early engagement. Quantitatively, the observed extensive exploration of strategies and low per-strategy execution time potetially facilitatates cybersecurity training on meta, i.e. strategic levels. At the same time, AI-assisted cybersecurity education introduces new challenges related to trust, dependency, and responsible use. We discuss implications for human-centered AI-supported cybersecurity education and outline open questions for future research.

cs.CR↗

arXiv2025

CAI Fluency: A Framework for Cybersecurity AI Fluency

This work introduces CAI Fluency, an an educational platform of the Cybersecurity AI (CAI) framework dedicated to democratizing the knowledge and application of cybersecurity AI tools in the global security community. The main objective of the CAI framework is to accelerate the widespread adoption and effective use of artificial intelligence-based cybersecurity solutions, pathing the way to vibe-hacking, the cybersecurity analogon to vibe-coding. CAI Fluency builds upon the Framework for AI Fluency, adapting its three modalities of human-AI interaction and four core competencies specifically for cybersecurity applications. This theoretical foundation ensures that practitioners develop not just technical skills, but also the critical thinking and ethical awareness necessary for responsible AI use in security contexts. This technical report serves as a white-paper, as well as detailed educational and practical guide that helps users understand the principles behind the CAI framework, and educates them how to apply this knowledge in their projects and real-world security contexts.

cs.CR↗

arXiv2025

Are LLMs (Really) Ideological? An IRT-based Analysis and Alignment Tool for Perceived Socio-Economic Bias in LLMs

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. Unlike traditional methods, IRT accounts for item difficulty, improving ideological bias estimation. We fine-tune two LLM families (Meta-LLaMa 3.2-1B-Instruct and Chat- GPT 3.5) to represent distinct ideological positions and introduce a two-stage approach: (1) modeling response avoidance and (2) estimating perceived bias in answered responses. Our results show that off-the-shelf LLMs often avoid ideological engagement rather than exhibit bias, challenging prior claims of partisanship. This empirically validated framework enhances AI alignment research and promotes fairer AI governance.

cs.AI↗

arXiv2023

Graph models for Cybersecurity -- A Survey

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 representing and analysing cyber-attack using graph models, i.e. attack graph (AG) formalisms. We propose a taxonomy on attack graph formalisms, based on 70 models, which we analysed with respect to their \textit{graph semantic}, involved agents and analysis features. Additionally, we adress which formalisms allow for automatic attack graph generation from raw or processes data inputs. Our taxonomy is especially designed to help users and applied researchers identify a suitable AG model for their needs. A summary of the individual AG formalisms is provided as supplementary material.

cs.CR↗

arXiv2021

Supervised Machine Learning with Plausible Deniability

We study the question of how well machine learning (ML) models trained on a certain data set provide privacy for the training data, or equivalently, whether it is possible to reverse-engineer the training data from a given ML model. While this is easy to answer negatively in the most general case, it is interesting to note that the protection extends over non-recoverability towards plausible deniability: Given an ML model $f$, we show that one can take a set of purely random training data, and from this define a suitable ``learning rule'' that will produce a ML model that is exactly $f$. Thus, any speculation about which data has been used to train $f$ is deniable upon the claim that any other data could have led to the same results. We corroborate our theoretical finding with practical examples, and open source implementations of how to find the learning rules for a chosen set of raining data.

cs.LG↗