Research
Research
Research
Research
222+ open-access research outputs.
Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitives. However, state-of…
The Production and Distributed Analysis (PanDA) system, originally developed for the ATLAS experiment at the CERN Large Hadron Collider (LHC), has evolved into a robust platform for orchestrating larg…
Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce Trojan-Speak, an adversarial fine-tuni…
Synthetic insider threat benchmarks face a consistency problem: corpora generated without an external factual constraint cannot rule out cross-artifact contradictions. The CERT dataset -- the field's …
Large-scale scientific collaborations, such as the Compact Muon Solenoid (CMS) at CERN, produce a vast and ever-growing corpus of internal documentation. Navigating this complex information landscape …
This paper presents a detailed case study of the T2_BR_SPRACE storage frontend architecture and its observed performance in high-intensity data transfers. The architecture is composed of a heterogeneo…
This paper contributes to the nascent debate around safety cases for frontier AI systems. Safety cases are structured, defensible arguments that a system is acceptably safe to deploy in a given contex…
Unix tools such as ls, cp, mv, and rename expose a filesystem abstraction that appears to present a single, authoritative state evolving through atomic transitions. This abstraction is false. We pre…
Insider threat detection is difficult because malicious behavior is rare, irregular, and buried in long periods of inactivity. In enterprise audit data, most windows contain little activity, while att…
Amazon published its Frontier Model Safety Framework (FMSF) as part of the Paris AI summit, following which we presented a report on Amazon's Premier model. In this report, we present an evaluation of…
Insider threats are a particularly tricky cybersecurity issue, especially in zero-trust architectures (ZTA) where implicit trust is removed. Although the rule of thumb is never trust, always verify, a…
Heterogeneous computing integrates diverse processing elements, such as CPUs, GPUs, and FPGAs, within a single system, aiming to leverage the strengths of each architecture to optimize performance and…
GitOps is a foundational approach for modernizing infrastructure by leveraging Git as the single source of truth for declarative configurations. The poster explores how GitOps transforms traditional c…
Frontier Large Language Models (LLMs) pose unprecedented dual-use risks through the potential proliferation of chemical, biological, radiological, and nuclear (CBRN) weapons knowledge. We present the …
Multimodal large language models (MLLMs) have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a syst…
This paper addresses the lifting problem for the \v{C}ern\'y conjecture: namely, whether the validity of the conjecture for a quotient automaton can always be transferred (or "lifted") to the original…
This project explores the development of an AI-enhanced operator assistant for UNICOS, CERN's UNified Industrial Control System. While powerful, UNICOS presents a number of challenges, including the c…
We develop a consolidated theory for the detectability of network-borne attacks under two canonical observation models: (i) a static graph drawn from an Erdos-Renyi background with a planted anomalous…
The integration of artificial intelligence (AI) into telecommunications infrastructure introduces novel risks, such as algorithmic bias and unpredictable system behavior, that fall outside the scope o…
We survey results in the literature that establish the \v{C}ern\'y conjecture for various classes of finite automata. We also list classes for which the conjecture remains open, but a quadratic (in th…
Free open-access publishing with Google Scholar indexing.
Submission Guide →