6 papers
Building to the Test: Coding Agents Deliver What You Check, Not What You Requested
Yanuo Ma, Ben Kereopa-Yorke, Ben Schultz
Benchmarks are widely used to evaluate task completion by Large Language Models (LLMs), but this approach has accumulated construction-validity problems, and a passing score may no…
Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning
Ben Kereopa-Yorke, Guillermo Diaz, Holly Wright +3
We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect co…
Engineering Trust, Creating Vulnerability: A Socio-Technical Analysis of AI Interface Design
Ben Kereopa-Yorke
This paper examines how distinct cultures of AI interdisciplinarity emerge through interface design, revealing the formation of new disciplinary cultures at these intersections. Th…
Quantifying AI Vulnerabilities: A Synthesis of Complexity, Dynamical Systems, and Game Theory
B Kereopa-Yorke
The rapid integration of Artificial Intelligence (AI) systems across critical domains necessitates robust security evaluation frameworks. We propose a novel approach that introduce…
ClausewitzGPT Framework: A New Frontier in Theoretical Large Language Model Enhanced Information Operations
Benjamin Kereopa-Yorke
In a digital epoch where cyberspace is the emerging nexus of geopolitical contention, the melding of information operations and Large Language Models (LLMs) heralds a paradigm shif…
Building Resilient SMEs: Harnessing Large Language Models for Cyber Security in Australia
Benjamin Kereopa-Yorke
The escalating digitalisation of our lives and enterprises has led to a parallel growth in the complexity and frequency of cyber-attacks. Small and medium-sized enterprises (SMEs),…