arXiv subjects

Xavier-Lewis Palmer

Publications and source records attributed to Xavier-Lewis Palmer.

11 recordsLinked to original sources

arXiv2026

Building AI-Ready Data Systems for Space Life Sciences, Aerospace Medicine, and Deep Space Exploration

While AI holds the potential to revolutionize space life sciences, realizing this promise is contingent upon the systematic restructuring of heterogeneous spaceflight biological data into machine-actionable, AI-ready forms. Even though open access principles support human reuse and scientific reproducibility, this does not necessarily enable AI systems to access and analyze such a diverse set of scientific datasets. In addition, the growing array of AI approaches places distinct demands on data structure, metadata, and access interfaces. In order to respond to such growing changes we propose a three-tier approach, proceeding from FAIR to AI-ready to space-ready data. We discuss existing infrastructures and how they can be improved to close the AI access gap. We conclude by proposing a neutral international coordinating body as the governance backbone for the trustworthy, agent-accessible space biology infrastructure that deep space biological research will require.

q-bio.OT↗

arXiv2026

Artificial Pancreas Implantables -- How Healthcare Professionals May Deal With DIY Bio Cases

Automated insulin delivery (AID) and artificial pancreas systems increasingly serve as safety-critical cyber-physical technologies in clinical care, integrating sensors, algorithms, software, and insulin-delivery hardware to automate a life-sustaining therapy. While regulated commercial systems are supported by formal approval pathways, manufacturer governance, and post-market surveillance, clinicians are also encountering patients who rely on do-it-yourself (DIY) artificial pancreas systems that operate outside conventional regulatory and institutional control structures. This paper examines how routine clinical handling practices intersect with cyberbiosecurity risk across both regulated and DIY AID systems. When insulin delivery systems are fundamentally reconfigured into a bespoke AID system, with the patient-user becoming the primary threat vector by assuming manufacturer-level roles without mandated governance, the entire ecosystem of stakeholders is placed in legal and clinical uncertainty.

cs.CR↗

arXiv2026

BioShield: A Context-Aware Firewall for Securing Bio-LLMs

The rapid advancement of Large Language Models (LLMs) in biological research has significantly lowered the barrier to accessing complex bioinformatics knowledge, ex perimental design strategies, and analytical workflows. While these capabilities accelerate innovation, they also introduce serious dual-use risks, as Bio-LLMs can be exploited to generate harmful biological insights under the guise of legitimate research queries. Existing safeguards, such as static prompt filtering and policy-based restrictions, are insufficient when LLMs are embedded within dynamic biological workflows and application-layer systems. In this paper, we present BioShield, a context-aware application-level firewall designed to secure Bio LLMs against dual-use attacks. At the core of BioShield is a domain-specific prompt scanner that performs contextual risk analysis of incoming queries. The scanner leverages a harmful scoring mechanism tailored to biological dual-use threat cat egories to identify prompts that attempt to conceal malicious intent within seemingly benign research requests. Queries ex ceeding a predefined risk threshold are blocked before reaching the model, effectively preventing unsafe knowledge generation at the source. In addition to pre-generation protection, BioShield deploys a post-generation output verification module that inspects model responses for actionable or weaponizable biological content. If an unsafe response is detected, the system triggers controlled regeneration under strengthened safety constraints. By combining contextual prompt scanning with response-level validation, BioShield provides a layered defense framework specifically designed for bio-domain LLM deployments. Our framework advances cyberbiosecurity by formalizing dual-use threat detection in Bio-LLMs and proposing a structured mitigation strategy for secure, responsible AI driven biological research.

cs.CR↗

arXiv2025

Safeguarding Smart Inhaler Devices and Patient Privacy in Respiratory Health Monitoring

The rapid development of Internet of Things (IoT) technology has significantly impacted various market sectors. According to Li et al. (2024), an estimated 75 billion devices will be on the market in 2025. The healthcare industry is a target to improve patient care and ease healthcare provider burdens. Chronic respiratory disease is likely to benefit from their inclusion, with 545 million people worldwide recorded to suffer from patients using these devices to track their dosage. At the same time, healthcare providers can improve medication administration and monitor respiratory health (Soriano et al., 2020). While IoT medical devices offer numerous benefits, they also have security vulnerabilities that can expose patient data to cyberattacks. It's crucial to prioritize security measures in developing and deploying IoT medical devices, especially in personalized health monitoring systems for individuals with respiratory conditions. Efforts are underway to assess the security risks associated with intelligent inhalers and respiratory medical devices by understanding usability behavior and technological elements to identify and address vulnerabilities effectively. This work analyses usability behavior and technical vulnerabilities, emphasizing the confidentiality of information gained from Smart Inhalers. It then extrapolates to interrogate potential vulnerabilities with Implantable Medical Devices (IMDs). Our work explores the tensions in device development through the intersection of IoT technology and respiratory health, particularly in the context of intelligent inhalers and other breathing medical devices, calling for integrating robust security measures into the development and deployment of IoT devices to safeguard patient data and ensure the secure functioning of these critical healthcare technologies.

cs.CR↗

arXiv2020

Biocybersecurity -- A Converging Threat as an Auxiliary to War

Biodefense is the discipline of ensuring biosecurity with respect to select groups of organisms and limiting their spread. This field has increasingly been challenged by novel threats from nature that have been weaponized such as SARS, Anthrax, and similar pathogens, but has emerged victorious through collaboration of national and world health groups. However, it may come under additional stress in the 21st century as the field intersects with the cyberworld -- a world where governments have already been struggling to keep up with cyber attacks from small to state-level actors as cyberthreats have been relied on to level the playing field in international disputes. Disruptions to military logistics and economies through cyberattacks have been able to be done at a mere fraction of economic and moral costs through conventional military means, making it an increasingly tempting means of disruption. In the field of biocybersecurity (BCS), the strengths within biotechnology and cybersecurity merge, along with many of their vulnerabilities, and this could spell increased trouble for biodefense, as novel threats can be synthesized and disseminated in ways that fuse the routes of attacks seen in biosecurity and cybersecurity. Herein, we offer an exploration of how threats in the domain of biocybersecurity may emerge through less foreseen routes as it might be an attractive auxiliary to conventional war. This is done through an analysis of potential payload and delivery methods to develop notional threat vectorizations. We conclude with several paradigms through which to view BCS-based threats.

cs.CY↗

arXiv2020

Brain-Computer Interfaces and the Dangers of Neurocapitalism

We review how existing trends are relevant to the discussion of brain-computer interfaces and the data they would generate. Then, we posit how the commerce of neural data, dubbed Neurocapitalism, could be impacted by the maturation of brain-computer interface technology. We explore how this could pose fundamental changes to our way of interacting, as well as our sense of autonomy and identity. Because of the power inherent in the technology, and its potentially ruinous abuses, action must be taken before the appearance of the technology, and not come as a reaction to it. The widespread adoption of brain-computer interface technology will certainly change our way of life. Whether it is changed for the better or worse, depends on how well we prepare for its arrival.

cs.HC↗

arXiv2020

Human Factors in Biocybersecurity Wargames

Within the field of biocybersecurity, it is important to understand what vulnerabilities may be uncovered in the processing of biologics as well as how they can be safeguarded as they intersect with cyber and cyberphysical systems, as noted by the Peccoud Lab, to ensure not only product and brand integrity, but protect those served. Recent findings have revealed that biological systems can be used to compromise computer systems and vice versa. While regular and sophisticated attacks are still years away, time is of the essence to better understand ways to deepen critique and grasp intersectional vulnerabilities within bioprocessing as processes involved become increasingly digitally accessible. Wargames have been shown to be successful with-in improving group dynamics in response to anticipated cyber threats, and they can be used towards addressing possible threats within biocybersecurity. Within this paper, we discuss the growing prominence of biocybersecurity, the importance of biocybersecurity to bioprocessing , with respect to domestic and international contexts, and reasons for emphasizing the biological component in the face of explosive growth in biotechnology and thus separating the terms biocybersecurity and cyberbiosecurity. Additionally, a discussion and manual is provided for a simulation towards organizational learning to sense and shore up vulnerabilities that may emerge within an organization's bioprocessing pipeline

cs.CR↗

arXiv2020

On the Emerging Area of Biocybersecurity and Relevant Considerations

Biocybersecurity is a novel space for the 21st century that meets our innovations in biotechnology and computing head on. Within this space, many considerations are open for and demand consideration as groups endeavor to develop products and policies that adequately ensure asset management and protection. Herein, simplified and brief exploration is given followed by some surface discussion of impacts. These impacts concern the end user, ethical and legal considerations, international proceedings, business, and limitations. It is hoped that this will be helpful in future considerations towards biocybersecurity policy developments and implementations. Notice: This article has been queued for publication in the Proceedings of the 2020 Future of Information and Communication Conference (FICC)

cs.CY↗

arXiv2018

CellLineNet: End-to-End Learning and Transfer Learning For Multiclass Epithelial Breast cell Line Classification via a Convolutional Neural Network

Computer Vision for Analyzing and Classifying cells and tissues often require rigorous lab procedures and so automated Computer Vision solutions have been sought. Most work in such field usually requires Feature Extractions before the analysis of such features via Machine Learning and Machine Vision algorithms. We developed a Convolutional Neural Network that classifies 5 types of epithelial breast cell lines comprised of two human cancer lines, 2 normal immortalized lines, and 1 immortalized mouse line (MDA-MB-468, MCF7, 10A, 12A and HC11) without requiring feature extraction. The Multiclass Cell Line Classification Convolutional Neural Network extends our earlier work on a Binary Breast Cancer Cell Line Classification model. CellLineNet is 31-layer Convolutional Neural Network trained, validated and tested on a 3,252 image dataset of 5 types of Epithelial Breast cell Lines (MDA-MB-468, MCF7, 10A, 12A and HC11) in an end-to-end fashion. End-to-End Learning enables CellLineNet to identify and learn on its own, visual features and regularities most important to Breast Cancer Cell Line Classification from the dataset of images. Using Transfer Learning, the 28-layer MobileNet Convolutional Neural Network architecture with pre-trained ImageNet weights is extended and fine tuned to the Multiclass Epithelial Breast cell Line Classification problem. CellLineNet simply requires an imaged Cell Line as input and it outputs the type of breast epithelial cell line (MDA-MB-468, MCF7, 10A, 12A or HC11) as predicted probabilities for the 5 classes. CellLineNet scored a 96.67% Accuracy.

cs.CV↗

arXiv2018

End-to-End Learning via a Convolutional Neural Network for Cancer Cell Line Classification

Computer Vision for automated analysis of cells and tissues usually include extracting features from images before analyzing such features via various Machine Learning and Machine Vision algorithms. We developed a Convolutional Neural Network model that classifies MDA-MB-468 and MCF7 breast cancer cells via brightfield microscopy images without the need of any prior feature extraction. Our 6-layer Convolutional Neural Network is directly trained, validated and tested on 1,241 images of MDA-MB-468 and MCF7 breast cancer cell line in an end-to-end fashion, allowing a system to distinguish between different cancer cell types. The model takes in as input imaged breast cancer cell line and then outputs the cell line type (MDA-MB-468 or MCF7) as predicted probabilities between the two classes. Our model scored a 99% Accuracy.

cs.CV↗

arXiv2018

ScaffoldNet: Detecting and Classifying Biomedical Polymer-Based Scaffolds via a Convolutional Neural Network

We developed a Convolutional Neural Network model to identify and classify Airbrushed (alternatively known as Blow-spun), Electrospun and Steel Wire scaffolds. Our model ScaffoldNet is a 6-layer Convolutional Neural Network trained and tested on 3,043 images of Airbrushed, Electrospun and Steel Wire scaffolds. The model takes in as input an imaged scaffold and then outputs the scaffold type (Airbrushed, Electrospun or Steel Wire) as predicted probabilities for the 3 classes. Our model scored a 99.44% Accuracy, demonstrating potential for adaptation to investigating and solving complex machine learning problems aimed at abstract spatial contexts, or in screening complex, biological, fibrous structures seen in cortical bone and fibrous shells.

cs.CV↗