Related papers: Auditing MCP Servers for Over-Privileged Tool Capa…
Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs offer cyber threat intelligence (CTI) to support vulnerability assessment and incident…
Multi-server MCP agents create an information-flow control problem: faithful tool composition can turn individually benign read/write permissions into cross-boundary credential propagation -- a structural side effect of workflow topology,…
The advance of web services technologies promises to have far-reaching effects on the Internet and enterprise networks allowing for greater accessibility of data. The security challenges presented by the web services approach are…
CPUs provide isolation mechanisms like virtualization and privilege levels to protect software. Yet these focus on architectural isolation while typically overlooking microarchitectural side channels, exemplified by Meltdown and Foreshadow.…
Controlled sharing is fundamental to distributed systems. We consider a capability-based distributed authorization system where a client receives capabilities (access tokens) from an authorization server to access the resources of resource…
Most software companies have extensive test suites and re-run parts of them continuously to ensure recent changes have no adverse effects. Since test suites are costly to execute, industry needs methods for test case prioritisation (TCP).…
Cybersecurity post-incident reviews are essential for identifying control failures and improving organisational resilience, yet they remain labour-intensive, time-consuming, and heavily reliant on expert judgment. This paper investigates…
With the rapid development of Large Language Models (LLMs), a large number of benchmarks have been proposed. However, most benchmarks lack unified evaluation standard and require the manual implementation of custom scripts, making results…
Agentic AI systems and Physical or Embodied AI systems have been two key research verticals at the forefront of Artificial Intelligence and Robotics, with Model Context Protocol (MCP) increasingly becoming a key component and enabler of…
Tabletop exercises are a crucial component of many company's strategy to test and evaluate its preparedness for security incidents in a realistic way. Traditionally led by external firms specializing in cybersecurity, these exercises can be…
As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce the first theoretical…
Collaborative machine learning (ML) is widely used to enable institutions to learn better models from distributed data. While collaborative approaches to learning intuitively protect user data, they remain vulnerable to either the server,…
Discrete Combinatorial Problems (DCPs) are prevalent in industrial decision-making and optimisation. However, while constraint solving technologies for DCPs have advanced significantly, the core process of formalising them, namely…
Large Language Model (LLM)-based agent systems are increasingly deployed for complex real-world tasks but remain vulnerable to natural language-based attacks that exploit over-privileged tool use. This paper aims to understand and mitigate…
The Model Context Protocol (MCP) introduces a standard specification that defines how Foundation Model (FM)-based agents should interact with external systems by invoking tools. However, to understand a tool's purpose and features, FMs rely…
In the rapidly evolving digital landscape, where organisations are increasingly vulnerable to cybersecurity threats, Cybersecurity Capability Maturity Models (CCMMs) emerge as pivotal tools in enhancing organisational cybersecurity posture.…
Recent improvements in large language models (LLMs) have had a dramatic effect on capabilities and productivity across many disciplines involving critical thinking and writing. The development of the model context protocol (MCP) provides a…
We present SACRO-ML, an integrated suite of open source Python tools to facilitate the statistical disclosure control (SDC) of machine learning (ML) models trained on confidential data prior to public release. SACRO-ML combines (i) a…
Many tools and libraries are readily available to build and operate distributed Web applications. While the setup of operational environments is comparatively easy, practice shows that their continuous secure operation is more difficult to…
Secure Multi-Party Computation (MPC) allows mutually distrusting parties to run joint computations without revealing private data. Current MPC algorithms scale poorly with data size, which makes MPC on "big data" prohibitively slow and…