Related papers: Enterprise-Grade Security for the Model Context Pr…
A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment risk management falls short: where either very dangerous…
Effective multi-agent systems cannot be designed by selecting prompts or communication graphs in isolation. Agent behavior depends on the information an agent receives, while the usefulness of a communication edge depends on how the…
The MITRE ATT&CK framework is a widely adopted tool for enhancing cybersecurity, supporting threat intelligence, incident response, attack modeling, and vulnerability prioritization. This paper synthesizes research on its application across…
The downstream use cases, benefits, and risks of AI models depend significantly on what sort of access is provided to the model, and who it is provided to. Though existing safety frameworks and AI developer usage policies recognise that the…
This white paper presents an analysis done by the MAMI project of the privacy and security concerns surrounding middlebox cooperation protocols (MCPs), based on our experimental experience with the Path Layer UDP Substrate (PLUS) proposal.…
Adversarial attacks for machine learning models have become a highly studied topic both in academia and industry. These attacks, along with traditional security threats, can compromise confidentiality, integrity, and availability of…
This article discusses how the gap between early 5G network threat assessments and an adversarial Tactics, Techniques, Procedures (TTPs) knowledge base for future use in the MITRE ATT&CK threat modelling framework can be bridged. We…
Air quality monitoring is central to environmental sustainability and public health, yet traditional systems remain difficult for non-expert users to interpret due to complex visualizations, limited interactivity, and high deployment costs.…
Large Language Model (LLM) agents increasingly interact with external systems through tool-calling protocols such as the Model Context Protocol (MCP). In prevailing architectures, the agent must reason about every tool invocation in every…
Agentic AI systems present both significant opportunities and novel risks due to their capacity for autonomous action, encompassing tasks such as code execution, internet interaction, and file modification. This poses considerable…
We introduce a novel framework for learning context-aware runtime monitors for AI-based control ensembles. Machine-learning (ML) controllers are increasingly deployed in (autonomous) cyber-physical systems because of their ability to solve…
Cybersecurity organizations are adapting to GenAI integration through modified frameworks and hybrid operational processes, with success influenced by existing security maturity, regulatory requirements, and investments in human capital and…
Bioinformatics tools are essential for complex computational biology tasks, yet their integration with emerging AI-agent frameworks is hindered by incompatible interfaces, heterogeneous input-output formats, and inconsistent parameter…
In this paper we present a framework for risk-averse model predictive control (MPC) of linear systems affected by multiplicative uncertainty. Our key innovation is to consider time-consistent, dynamic risk metrics as objective functions to…
Analytical methods underpin geotechnical engineering practice, yet their implementation remains fragmented across error-prone spreadsheets and opaque proprietary software. While Large Language Models (LLMs) offer transformative potential…
The Observational Medical Outcomes Partnership (OMOP) common data model (CDM) provides a standardized representation of heterogeneous health data to support large-scale, multi-institutional research. One critical step in data…
Machine learning is being integrated into a growing number of critical systems with far-reaching impacts on society. Unexpected behaviour and unfair decision processes are coming under increasing scrutiny due to this widespread use and its…
Cryptographic Protocols (CP) are distributed algorithms intended for secure communication in an insecure environment. They are used, for example, in electronic payments, electronic voting procedures, systems of confidential data processing,…
The complex and evolving threat landscape of frontier AI development requires a multi-layered approach to risk management ("defense-in-depth"). By reviewing cybersecurity and AI frameworks, we outline three approaches that can help identify…
The remarkable capability of large language models (LLMs) has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context protocol (MCP)…