arXiv subjects

Simon Parkinson

Publications and source records attributed to Simon Parkinson.

14 recordsLinked to original sources

arXiv2026

Does Showing Agents the Privilege of Their Tools Reduce Over-Privileged Tool Selection?

When several tools can complete a task, an agent that picks the most powerful one holds more authority than the task needs. Recent work demonstrates that language-model agents do this often, and more so after a tool fails. Approaches to restrict focus so far on either enforcing least privilege outside the model or retraining the model. We ask a simpler question: does it help to tell the agent what each tool's privilege is? To investigate this question, we run all 544 ToolPrivBench scenarios on eight models, three run locally, and five through a hosted API, under five conditions: (1) no signal, (2) a least-privilege instruction, (3) privilege class and cost shown in each tool description, (4) both the instruction and privilege information, and (5) a matched neutral-metadata control. Showing privilege lowers premature escalation on every model that over-privileges at a measurable rate, reducing over-privileged selection by up to 19.3 percentage points (50\%), whereas irrelevant metadata in the same format does not. On most models, however, information alone mainly delays escalation until the standard tools have been tried. Combined with the instruction it more often avoids escalation, and the share of scenarios completed without a risk tool rises on seven of the eight models, reaching 51.1\% safe completion from a baseline of 18.8\% on the strongest-performing configuration. Visible privilege is therefore a cheap complement to enforcement rather than a substitute.

cs.CR↗

arXiv2026

Towards Elastic Least Privilege for Agent Planning

General-purpose AI agents require authority that changes between tasks and during execution. Common deployments trade broad permissions that expose unnecessary authority and narrow permissions that raise approval requests. Existing mechanisms can enforce dynamic authority, but agent tool interfaces rarely provide the agent's planner, the component that chooses its actions, a means of comparing the authority required by alternative actions or of seeing the cost of the authority it already holds. Drawing on the rich history of access control research, we propose the concept of \emph{elastic least privilege}, in which an agent begins with a small baseline of authority and may acquire more within an owner-defined envelope. Elevations are leased and measured against a replenishing budget. Their cost increases with power, proximity to mandatory safety invariants, and repeated requests. Costs are visible to the planner, which can prefer lower-privilege choices and release authority it no longer needs. Authority returns automatically to the baseline when a lease expires, when it is released, or when the budget is exhausted, while persistent legitimate demand may prompt an owner-approved change to the baseline. Building on prior risk-priced and budget-aware access control, we redesign these mechanisms for agents. How best to implement the approach and how well it works in practice are open research questions. In this paper, we present how the approach could work, illustrate the model, and set an open research agenda.

cs.CR↗

arXiv2026

Caption-Mediated Perceived-Safety Estimation for Pedestrian Routing

This paper presents an explainable approach to pedestrian routing, in which perceived safety is estimated from street-level imagery through an explicit natural-language intermediate representation. A vision--language model caption is generated and stored before any scoring is undertaken, and the perceived-risk class is derived entirely from structured features of that stored text, so that every segment score remains inspectable by the user. Nine captioning conditions across five model families are benchmarked against a direct Contrastive Language--Image Pre-training (CLIP) image-embedding baseline under an identical downstream pipeline, and the caption-mediated representation is found to reach parity with the image embedding rather than to trail it. The approach was deployed over 654,115 images covering 36 electoral wards in two locations in Northern England (Manchester and Huddersfield). Independent field validation against 3,669 locally collected ratings of 494 images across 70 participant sessions established agreement that is statistically significant but modest, at $r=0.262$, against a measured noise ceiling of 0.737 imposed by disagreement between raters. A single-use confirmatory test then found that a pipeline 44\% stronger on the supervised benchmark did not produce measurable improvement in the field ($r=0.250$, $p=0.84$), so the benchmark gains did not predict the deployment gains in this case. Routing behaviour varies systematically with journey length. There is negligible change below 1\,km, reaching a median increase of 12.78\% in low-risk route length for a median detour of 2.73\% on journeys of 3 to 6 km.

cs.CV↗

arXiv2026

Template Ageing and Longitudinal Verification in Fixed-Text Keystroke Dynamics: A Subject-Disjoint Study Across Eight Weeks

Behavioural biometric templates are widely believed to degrade as the gap between enrolment and verification grows, but few studies measure this template ageing effect directly under controlled conditions. We collected a longitudinal dataset of 40 fixed passwords, each typed four times per weekly session over eight consecutive weeks. We compare a scaled-Manhattan matcher (M1), a gradient-boosted classifier (M2), a TypeNet-style recurrent embedding model (M3), and a TypeFormer-style Transformer (M4) under a 5-fold subject-disjoint protocol and a design that jointly varies mechanism and the enrolment-to-query gap, from 0 to 7 weeks. Template ageing proves large and systematic. Error increases monotonically with the gap for every mechanism, from an EER of 14.6-27.2% at a gap of zero to 25.5-37.1% at seven weeks, or 1.7% of decision error per week elapsed (p < 0.001). However, the choice of mechanism matters more than its rate of ageing. Baseline accuracy spans 12.6 percentage points across the four mechanisms, the degradation each accumulates over seven weeks spans only 2.3 points, and ageing never reorders them. A matcher can therefore be chosen on same-session accuracy, with ageing managed by re-enrolment scheduling rather than by matcher selection. The two properties are nonetheless distinct, as M3 is the least accurate mechanism yet ages significantly more slowly than M1 under every specification tested. Training randomness also matters differently by architecture, with 58% of the recurrent model's fold-to-fold variance attributable to seed noise against 19% for the Transformer. Because the smaller ageing-rate differences are sensitive to modelling choices, while the accuracy differences and the ageing effect are not, we recommend that comparative ageing-rate claims be supported by seed-level score fusion, independent replication, and an alternative outcome-model specification.

cs.CR↗

arXiv2026

Why Commodity WiFi Sensors Fail at Multi-Person Gait Identification: A Systematic Analysis Using ESP32

WiFi Channel State Information (CSI) has shown promise for single-person gait identification, raising interest in its use for contactless biometrics, continuous authentication, and passive identification. However, the feasibility of multi-person identification on low-cost commodity devices remains unclear. A critical question is whether weak multi-person performance is primarily an algorithmic limitation, or whether it reflects a more fundamental sensing ceiling on commodity WiFi hardware. We address this question through a systematic empirical study using commodity ESP32 WiFi sensors. We evaluated six different signal separation methods--FastICA, SOBI, PCA-ICA, NMF, Wavelet, and Tensor decomposition--across seven scenarios spanning 1-10 people in both controlled and realistic indoor environments. To investigate beyond classification accuracy, we introduce three diagnostic metrics: intra-subject variability (ISV), inter-subject distinguishability (ISD), and performance degradation rate (PDR). In all methods, performance remains moderate (39%-56% accuracy), with limited evidence that algorithmic choice alone solves the problem. The best-performing method, NMF, reaches 56% accuracy, while all methods exhibit extremely high feature-space overlap (97%-99%), unstable within-subject representations, and marked environmental sensitivity. These findings suggest that, under commodity ESP32 CSI constraints, dense multi-person gait identification is limited more by sensing quality and spatial diversity than by the chosen separation algorithm. Our results have direct implications for security and privacy: they call into question the practicality of commodity WiFi CSI as a robust multi-user biometric primitive for authentication, while also placing important bounds on the passive identification capabilities achievable with low-cost off-the-shelf WiFi hardware.

cs.CV↗

arXiv2026

Fine-Tuning Small Language Models for Solution-Oriented Windows Event Log Analysis

Large language models (LLMs) have shown promise for event log analysis, but their high computational requirements, reliance on cloud infrastructure, and security concerns limit practical deployment. In addition, most existing approaches focus only on the identification of the problem and do not provide actionable remediation. Small language models (SLMs) present a light-weight alternative that can be fine-tuned for a specific purpose and hosted locally. This paper investigates whether SLMs, when fine-tuned for a specific task, can serve as a practical alternative for event log analysis while also generating solutions. We first create a large-scale synthetic Windows event log dataset that contains remediation actions using a high-performing LLM. We then fine-tune multiple SLMs and LLMs using the LoRA parameter-efficient fine-tuning technique and evaluate their performance by comparing with expert assessment. The results show that the dataset accurately reflects real-world scenarios and that fine-tuned SLMs consistently outperform LLMs in identifying issues and providing relevant remediation, while requiring fewer computational resources.

cs.CR↗

arXiv2026

Reproducibility in Event-Log Research: A Parametrised Generator and Benchmark for Event-based Signatures

Event-based datasets are crucial for cybersecurity analysis. A key use case is detecting event-based signatures, which represent attacks spanning multiple events and can only be understood once the relevant events are identified and linked. Analysing event datasets is essential for monitoring system security, but their growing volume and frequency create significant scalability and processing difficulties. Researchers rely on these datasets to develop and test techniques for automatically identifying signatures. However, because real datasets are security-sensitive and rarely shared, it becomes difficult to perform meaningful comparative evaluation between different approaches. This work addresses this evaluation limitation by offering a systematic method for generating event logs with known ground truth, enabling reproducible and comparable research. We present a novel parametrised generation technique capable of producing synthetic event datasets that contain event-based signatures for discovery. To demonstrate the capabilities of the technique, we provide a benchmark in signature detection. Our benchmarking demonstrated the suitability of DBSCAN, achieving a score greater than 0.95 Adjusted Rand Index on most generated datasets. This work enhances the ability of researchers to develop and benchmark new cybersecurity techniques, ultimately contributing to more robust and effective cybersecurity measures.

cs.CR↗

arXiv2026

Parameter-Efficient Domain Adaption for CSI Crowd-Counting via Self-Supervised Learning with Adapter Modules

Device-free crowd-counting using WiFi Channel State Information (CSI) is a key enabling technology for a new generation of privacy-preserving Internet of Things (IoT) applications. However, practical deployment is severely hampered by the domain shift problem, where models trained in one environment fail to generalise to another. To overcome this, we propose a novel two-stage framework centred on a CSI-ResNet-A architecture. This model is pre-trained via self-supervised contrastive learning to learn domain-invariant representations and leverages lightweight Adapter modules for highly efficient fine-tuning. The resulting event sequence is then processed by a stateful counting machine to produce a final, stable occupancy estimate. We validate our framework extensively. On our WiFlow dataset, our unsupervised approach excels in a 10-shot learning scenario, achieving a final Mean Absolute Error (MAE) of just 0.44--a task where supervised baselines fail. To formally quantify robustness, we introduce the Generalisation Index (GI), on which our model scores near-perfectly, confirming its ability to generalise. Furthermore, our framework sets a new state-of-the-art public WiAR benchmark with 98.8\% accuracy. Our ablation studies reveal the core strength of our design: adapter-based fine-tuning achieves performance within 1\% of a full fine-tune (98.84\% vs. 99.67\%) while training 97.2\% fewer parameters. Our work provides a practical and scalable solution for developing robust sensing systems ready for real-world IoT deployments.

cs.CV↗

arXiv2025

Document Retrieval Augmented Fine-Tuning (DRAFT) for safety-critical software assessments

Safety critical software assessment requires robust assessment against complex regulatory frameworks, a process traditionally limited by manual evaluation. This paper presents Document Retrieval-Augmented Fine-Tuning (DRAFT), a novel approach that enhances the capabilities of a large language model (LLM) for safety-critical compliance assessment. DRAFT builds upon existing Retrieval-Augmented Generation (RAG) techniques by introducing a novel fine-tuning framework that accommodates our dual-retrieval architecture, which simultaneously accesses both software documentation and applicable reference standards. To fine-tune DRAFT, we develop a semi-automated dataset generation methodology that incorporates variable numbers of relevant documents with meaningful distractors, closely mirroring real-world assessment scenarios. Experiments with GPT-4o-mini demonstrate a 7% improvement in correctness over the baseline model, with qualitative improvements in evidence handling, response structure, and domain-specific reasoning. DRAFT represents a practical approach to improving compliance assessment systems while maintaining the transparency and evidence-based reasoning essential in regulatory domains.

cs.SE↗

arXiv2025

Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models: A Railway Casestudy

Operational Technology Cybersecurity (OTCS) continues to be a dominant challenge for critical infrastructure such as railways. As these systems become increasingly vulnerable to malicious attacks due to digitalization, effective documentation and compliance processes are essential to protect these safety-critical systems. This paper proposes a novel system that leverages Large Language Models (LLMs) and multi-stage retrieval to enhance the compliance verification process against standards like IEC 62443 and the rail-specific IEC 63452. We first evaluate a Baseline Compliance Architecture (BCA) for answering OTCS compliance queries, then develop an extended approach called Parallel Compliance Architecture (PCA) that incorporates additional context from regulatory standards. Through empirical evaluation comparing OpenAI-gpt-4o and Claude-3.5-haiku models in these architectures, we demonstrate that the PCA significantly improves both correctness and reasoning quality in compliance verification. Our research establishes metrics for response correctness, logical reasoning, and hallucination detection, highlighting the strengths and limitations of using LLMs for compliance verification in railway cybersecurity. The results suggest that retrieval-augmented approaches can significantly improve the efficiency and accuracy of compliance assessments, particularly valuable in an industry facing a shortage of cybersecurity expertise.

cs.AI↗

arXiv2025

LLM-based event log analysis techniques: A survey

Event log analysis is an important task that security professionals undertake. Event logs record key information on activities that occur on computing devices, and due to the substantial number of events generated, they consume a large amount of time and resources to analyse. This demanding and repetitive task is also prone to errors. To address these concerns, researchers have developed automated techniques to improve the event log analysis process. Large Language Models (LLMs) have recently demonstrated the ability to successfully perform a wide range of tasks that individuals would usually partake in, to high standards, and at a pace and degree of complexity that outperform humans. Due to this, researchers are rapidly investigating the use of LLMs for event log analysis. This includes fine-tuning, Retrieval-Augmented Generation (RAG) and in-context learning, which affect performance. These works demonstrate good progress, yet there is a need to understand the developing body of knowledge, identify commonalities between works, and identify key challenges and potential solutions to further developments in this domain. This paper aims to survey LLM-based event log analysis techniques, providing readers with an in-depth overview of the domain, gaps identified in previous research, and concluding with potential avenues to explore in future.

cs.AI↗

arXiv2024

Cognitive Effort Measures Driven by Fixation Induced Retinal Flow in Visual Scanning Behavior during Virtual Driving

In this paper, we consider the problem of visual scanning mechanism underpinning sensorimotor tasks, such as walking and driving, in dynamic environments. We exploit eye tracking data for offering two new cognitive effort measures in visual scanning behavior of virtual driving. By utilizing the retinal flow induced by fixation, two novel measures of cognitive effort are proposed through the importance of grids in the viewing plane and the concept of information quantity, respectively. Psychophysical studies are conducted to reveal the effectiveness of the two proposed measures. Both these two cognitive effort measures have shown their significant correlation with pupil size change. Our results suggest that the quantitative exploitation of eye tracking data provides an effective approach for the evaluation of sensorimotor activities.

cs.HC↗

arXiv2013

A Novel Software Tool for Analysing NT File System Permissions

Administrating and monitoring New Technology File System (NTFS) permissions can be a cumbersome and convoluted task. In today's data rich world there has never been a more important time to ensure that data is secured against unwanted access. This paper identifies the essential and fundamental requirements of access control, highlighting the main causes of their misconfiguration within the NTFS. In response, a number of features are identified and an efficient, informative and intuitive software-based solution is proposed for examining file system permissions. In the first year that the software has been made freely available it has been downloaded and installed by over four thousand users

cs.SE↗

arXiv2011

Comfort-constrained distributed heat pump management

This paper introduces the design of a demand response network control strategy aimed at thermostatically controlled electric heating and cooling systems in buildings. The method relies on the use of programmable communicating thermostats, which are able to provide important component-level state variables to a system-level central controller. This information can be used to build power density distribution functions for the aggregate heat pump load. These functions lay out the fundamental basis for the methodology by allowing for consideration of customer-level constraints within the system-level decision making process. The proposed strategy is then implemented in a computational model to simulate a distribution of buildings, where the aggregate heat pump load is managed to provide the regulation services needed to successfully integrate wind power generators. Increased exploitation of wind resources will place similarly themed ancillary services in high-demand, traditionally provided by dispatchable energy resources that are ill-suited for the frequent power gradients that accompany wind power generation.

math.OC↗