Biological aging clocks estimate age from molecular data and provide insights into age-related functional decline. While aging clocks based on bulk transcriptomic data are well-studied, their single-cell counterparts remain limited and underexplored. In this study, we replicate and enhance a recent single-cell RNA-seq aging clock for human immune cells using ElasticNet, improving its performance through refined preprocessing, feature selection, and regularization. We also explore LightGBM to assess nonlinear modeling potential. Our enhanced models reduce prediction error, generalize better across external datasets, and identify biologically relevant genes through SHAP analysis. These findings support the development of accurate, interpretable, cell-type-specific aging clocks using single-cell data.

The aim of this research is to investigate whether physical gene characteristics can predict age-related changes in gene expression. Specifically, we analyze gene length, GC content, distance to the ends of the chromosome, and similar features to determine their connection with differential expression between young and old individuals. Among these features, gene length consistently shows a strong correlation with age-related expression patterns. However, when combined, the selected features do not provide sufficient predictive power to train a classifier capable of exceeding a modest 66% accuracy. These findings highlight the limitations of the current feature set and point toward the need for more complex feature preprocessing steps or biologically relevant features in future predictive models.

Aging is the biological process that changes the body over time. When we age our bodies become more prone to disease and other health risks. But not everyone experiences these changes at the same age. This is because the age of our cells (biological age) does not always match our chronological age (time since birth). Being able to predict someone’s biological age and comparing it to their chronological age can be used to infer if someone is indeed more prone to diseases or other health risks.

Other studies have been able to predict the age of cells by using gene expressions. They explore the number of expressions in young and old individuals to identify genes that are affected by age. What has not yet been explored is how the correlation of gene pairs are affected by age. How genes cooperate can change with age, this can be captured by looking at how genes correlate and how that correlation changes with age. This paper will explore these correlations and answer the following question. By performing a correlation analysis between features of young individuals, and on the same features for old individuals, can we interpret any differences and use those to improve current age prediction models?

During this study we found a lot of gene pairs that have a significant difference in correlation from younger to older individuals. We also identified hub genes that change correlation with many other genes. Using these genes to train a linear regression model we were able to predict the age of cells with a Mean Absolute Error of 9.7835.

Using the hub genes we were not able to improve the current existing linear regression model. But we did identify genes that have earlier been linked to aging. Like LIMD2, but also a lot of ribosomal genes and mitochondrial genes, both of which lose functionality with aging.

Understanding the mechanisms of aging can help us live longer and healthier lives. Epigenetic age predictors are machine learning models that use methylation levels at CpG sites to predict the biological age of the cell. Horvath’s linear clock uses 353 CpGs with a median absolute error (MedAE) of 3.530, while the deep learning model AltumAge uses 20,318 CpGs to achieve a MedAE of 2.147. This study explores how to improve the accuracy of age predictors through model architecture selection, hyperparameter optimization, and feature selection. ElasticNet regression with recursive feature elimination achieved a MedAE of 2.820 using 341 CpGs, outperforming Horvath’s clock. The two models shared 95 CpG sites, and gene enrichment analysis revealed that several associated genes are involved in stem cell regulation. Feature importance and model interpretation were performed using SHAP analysis, which indicated that age prediction cannot be captured by a small subset of CpG sites. It was concluded that epigenetics has an influence on stem cells, which was found to be a biomarker of aging. Aging remains a complex process that deep learning models may capture better.

Early detection of leprosy, a neglected tropical disease, is crucial to preventing irreversible nerve damage and disability. Analyzing temperature vari- ations in hands using infrared (IR) cameras offers a potential low-cost alternative to existing medical equipment for early detection of leprosy. This study explores the adaptation of hand landmark detec- tion models, commonly used for hand pose track- ing, to infer the hypothenar area, a critical region for leprosy diagnosis. The research addresses the challenge of limited ground-truth data for the hy- pothenar keypoint by developing annotated datasets and evaluating machine learning models like Lasso Regression and XGBoost. These models signif- icantly outperform the existing method of linear interpolation, demonstrating the feasibility of ac- curate hypothenar keypoint prediction even with limited training data. The findings contribute to the development of accessible, automated tools for early leprosy diagnosis, particularly in resource- constrained settings.

Leprosy remains a significant health challenge in developing countries, where early diagnosis is crucial to prevent severe disabilities and social stigma. Recent studies have shown that infrared imaging can be used to detect abnormalities associated with leprosy by analyzing hand temperature variations. However, existing diagnostic methods relying on manual annotation of thermal images are timeconsuming, lack standardization, and require technical expertise. This research investigates methods for implementing real-time infrared video-based temperature analysis on mobile devices by focusing on hand landmark detection models, model optimization techniques, and evaluation metrics. A comprehensive literature review identified promising models such as MediaPipe Hands, OpenPose, and YOLO variants for hand landmark detection, along with optimization methods like pruning, quantization, and Neural Architecture Search (NAS) to adapt these models for mobile deployment. Furthermore, evaluation frameworks incorporating both performance and capability-oriented metrics were examined to ensure efficient and reliable deployment on resource-constrained devices. This study provides insights into developing a fully automated, mobile-based diagnostic tool for early leprosy detection, highlighting the challenges and opportunities in adapting visual AI models for infrared analysis. Future research should focus on empirical validation of optimized models on mobile platforms.

In this work, we investigate how domain adaptation techniques can improve the performance of hand landmark detection models originally trained on RGB images when deployed on infrared (IR) data. Our motivation stems from a medical use case in Nepal, where clinicians require reliable temperature estimation at hand keypoints to detect early signs of leprosy. We evaluate three methods on a small IR dataset (80 labeled images & 5000 unlabeled frames): a shallow adaptation (AdaBN), a deep alignment approach (Deep CORAL), and a test-time subspace alignment method (SSA). Our experiments show that while AdaBN and SSA yield moderate improvements, Deep CORAL achieves stronger gains through targeted training of specific model components. The combination of these methods produces superior results, yielding an 11% improvement in percentage of correct keypoints (PCK@0.05) on our custom annotated IR dataset. These findings demonstrate that combining lightweight and deep domain adaptation approaches can effectively enhance IR hand landmark detection accuracy without requiring large labeled datasets, enabling practical deployment for clinical thermal imaging in resource-limited settings.

Hand landmark detection in infrared (IR) images is essential for early leprosy diagnosis in developing countries like Nepal, helping to prevent serious complications and disability. However, current hand landmark detection models, such as Google’s detection models comprised in the MediaPipe framework, often struggle with this task due to domain mismatch. While these models are trained on RGB images, the data for this research consists of greyscale IR images. This study addresses this challenge by exploring image transformation and colorization techniques to enhance MediaPipe's hand landmark recognition accuracy on IR images. Preprocessing was chosen over retraining the existing model due to limited computational resources and the lack of labeled target domain data, which makes the retraining infeasible.

Two preprocessing pipelines were developed to address different image characteristics: images with visible hand edges but varying colors of the hand, and images where hands blend in with the background, making the edges difficult to distinguish. The transformations include turning an image into its negative, colorization, contrast enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE), and masking to remove occlusion.

To evaluate the effectiveness of these techniques, accuracy has been calculated using Percentage of Correct Keypoints (PCK) metric and were compared against two baselines: a lower bound (MediaPipe performance on unchanged IR images) and an upper bound (MediaPipe performance on similar RGB images). Preliminary findings indicate that colorization significantly improves recognition for hands with sharp color transition, while contrast enhancement boosts edge definition for hands that blend into the background. By combining these approaches, the overall accuracy of hand landmark detection improved up to 25%, depending on the threshold value, particularly for the targeted open palm-up hand position.

These results demonstrate that preprocessing techniques can effectively reduce the input domain mismatch, enhancing automated leprosy diagnosis and supporting early detection efforts in low-resource settings.

This study investigates sensor technologies for di- agnosing leprosy in Nepal, focussing on skin tem- perature in the hands using contact and non-contact sensors. Leprosy affects the peripheral nervous system, causing thermoregulatory dysfunction de- tectable via localized skin temperature changes. A systematised comparative review compares contact thermometry, infrared (IR) thermography, and IR- RGB thermography based on measurement quality, usability, and cost. Next to the systematised re- view, an experimental method is proposed to com- bine RGB and IR imaging to enhance the spatial accuracy of automatic region of interest (ROI) de- tection using MediaPipe Hand Landmarker. The study introduces a multimodal dataset of 45 sets of annotated IR-RGB images and validates a geomet- rical image registration model, achieving 93.2% keypoint detection accuracy—significantly outper- forming IR-only sensors. Results show IR-RGB thermography as a cost-effective, flexible, and ac- curate tool for early leprosy diagnosis in resource- limited settings.

Large Language Models (LLMs) are increasingly used in software development, but their potential for misuse in generating harmful code, such as malware, raises significant concerns. We present a red-teaming approach to assess the safety and ethical alignment of LLMs in the context of code generation, in particular how it applies to the generation of malware. By developing a dataset of prompts that are likely to elicit harmful behavior from the LLMs, we aim to provide a valuable resource for benchmarking the harmlessness factor of these models. Using this dataset, we evaluate multiple state-of-the-art open-source LLMs, analyzing factors such as model size, training alignment, and prompt specificity. Our findings show that LLMs vary significantly in their likelihood to generate harmful code, depending on factors like training data, alignment techniques, and prompt specificity. Furthermore, we demonstrate that system prompts could significantly alter the model's response to potentially harmful queries. We also demonstrate the efficacy of using LLMs to evaluate the harmlessness of other LLMs' responses. This research highlights the importance of ongoing development of safety measures to mitigate the risks associated with code-generating LLMs.

The rapid advancement of large language models has enabled numerous innovative, but also harmful applications. It is therefore essential to create these models to behave safely and responsibly. One way to improve these models is by red teaming them. In this study, we aim to identify prompts that lead large language models to exhibit unfair or dangerous behavior in software and cybersecurity contexts. We do this by manually creating prompts and manually assessing the harmfulness of the response. Our contributions include a taxonomy of dangerous and unfair use cases of large language models for Code, a dataset of 200 prompts tested on eight models, an investigation into how expanding the prompt, and how adding a code skeleton for the model to complete changes the level of harmfulness. Among the eight models evaluated, only CodeGemma and GPT-3.5-0125 were well-aligned against our taxonomy categories. The unaligned Dolphin-Mixtral and self-aligned Starcoder 2 were notably susceptible to harmful responses across all categories. We observed that the Model Attacks category was problematic for most models. Expanding prompts increased harmful responses in the Cyber Attacks, Model Attacks, and Phishing categories but decreased them in the Biased Code Generation category. Adding a code skeleton to prompts consistently raised harmfulness across all categories. Large language model alignment still needs further improvement, so we suggest employing red teaming techniques to enhance the safety features of large language models.

Large Language Models (LLMs) have experienced a rapid increase in usage across numerous sectors in recent years. However, this growth brings a greater risk of misuse. This paper explores the issue of copyright infringement facilitated by LLMs in the domain of software engineering. Through the creation of a taxonomy and prompt engineering, we investigate how alignment, structure and language of prompts affect the behavior of LLMs against copyright infringing prompts, assessing their willingness to engage in copyright violation. Our findings underscore the critical role of model alignment in identifying potentially infringing inputs, irrespective of model complexity or modality. Notably, prompts that are crafted to avoid overtly malicious language, especially those that instruct the model to complete the input given, tend to yield more responses that could facilitate malicious activities. This research provides a preliminary understanding of copyright infringement by LLMs in software engineering and suggests avenues for future research.

Streamlined Byzantine Fault Tolerant (BFT) protocols, such as HotStuff [PODC'19], and weighted voting represent two possible strategies to improve consensus in the distributed systems world. Several studies have been conducted on both techniques, but the research on combining the two is scarce. To cover this knowledge gap, we introduce a weighted voting approach on Hotstuff, along with two optimisations targeting weight assignment distribution and leader rotation in the underlying state replication protocol. Moreover, the weighted protocols developed rely on studies proving the effectiveness of a specific voting power assignment based on discrete values. We generalise this approach by presenting a novel continuous weighting scheme applied to the Hotstuff protocol to highlight the effectiveness of this technique in faulty scenarios. We prove the significant latency reduction impact of weighted voting on streamlined protocols and advocate for further research.

This paper explores the integration of weighted vot-ing mechanisms into DAG-based consensus proto-cols, such as Tusk [EuroSys’22], which promise high throughput and low latency. Weighted voting,
pioneered by protocols like WHEAT [SRDS’15] and AWARE [TDSC’20], aims to optimize perfor-mance metrics such as latency and throughput by assigning weights to nodes based on their latency with other nodes. We employ real-world latency data from CloudPing to evaluate the impact of weighted voting on Tusk, comparing them against its unweighted counterpart. Our results demon-strate significant performance improvements, with the weighted voting mechanism achieving up to 37% lower consensus latency compared to un-weighted approaches.

This research addresses the challenge of managing latency in distributed computer systems. Maintaining correct delays in data transmission across various network conditions is crucial for system efficiency and security. We focus on improving the Adaptive Wide-Area Replication (AWARE) algorithm, a method used to coordinate data across different locations in a way that minimizes delays. To enhance AWARE, we incorporate two concepts: Vivaldi network coordinates and New- tonian invariants. Vivaldi network coordinates help the system better understand and calculate the physical layout of the network by embedding network members in Euclidean space, where the distance in this space represents latency be- tween them. Newton invariants are rules based on physics that help the system detect and adjust for any unusual changes in network latency that might be caused by technical issues or security threats. We evaluated the original and enhanced AWARE algorithms by simulating typical network operations and various attack scenarios designed to slow down the process of reaching consensus. Our findings show that the enhanced AWARE algorithm provides more accurate and robust management of network latency, especially under attack conditions, leading to a more reliable and secure distributed system. This study confirms that integrating correction techniques into latency management processes significantly improves the resilience and accuracy of distributed systems.

Sound pollution is becoming an increasingly pressing issue in today’s world. To effectively address it, it must be measured. To this end, Serval was developed, an edge-ai powered sound recognition solution. Its lack of accuracy, however, makes it difficult to deploy. This thesis examines the potential for improving this solution while staying within its technical limitations in order to raise the accuracy to satisfactory levels. Multiple aspects of Serval were evaluated and compared to the current stateof-the-art: its data augmentation, the embedding it uses, and the hardware it runs on. Alternatives for each of these components were evaluated and each aspect was optimized.
The results show that after these improvements, the single-label F1-score increased from 0.60 to 0.76, and the single- and multi-label combined F1-score increased from 0.64 to 0.67. Finally, power consumption has been reduced by 14%, partially thanks to the usage of specialized hardware. One issue that has yet to be adequately addressed is the size of the dataset. By increasing the number of samples, the accuracy could be further improved.

The rapid evolution of 5G technology has paved the way for the proliferation of resource-constrained Internet of Things (IoT) devices, collectively known as ambient IoT. While these devices offer unprecedented opportunities for connectivity and data collection, their limited computational capabilities present significant challenges in implementing robust security measures. This thesis addresses these challenges by proposing two novel lightweight security protocols tailored for ambient IoT devices within 5G networks.

The first protocol, "Lightweight security protocol instantiated using ASCON", leverages the ASCON family of cryptographic functions to ensure essential security properties while adhering to the constraints of ambient IoT devices. The protocol’s effectiveness is evaluated through simulations, focusing on computational efficiency compared to existing solutions.

The second protocol, "Data container-based security protocol", adopts a container-based approach to enhance interoperability and standardization across diverse ambient IoT device applications. This protocol facilitates seamless integration and compatibility among ambient IoT systems by encapsulating authentication and communication data within generic containers. The benefits of this approach are analyzed theoretically, highlighting its potential for standardization in heterogeneous 5G environments.

Together, these lightweight security protocols contribute to developing a secure and efficient ecosystem for ambient IoT devices within 5G networks. By addressing the challenges posed by resource-constrained devices and promoting interoperability, this thesis aims to enhance security and facilitate the widespread adoption of ambient IoT technologies in our increasingly connected world.

Hidden spy cameras are a growing worldwide threat to people’s intimacy and privacy. With the growing interest in full-screen devices and the underlying development of under-screen cameras, a new type of potential security risk is introduced. Recent smartphones such as the ZTE AXON 40 already demonstrate that it’s infeasible to detect the camera with the human eye. There exist several techniques to detect hidden cameras, however most of these techniques are not resilient to the unique deployment scenario of the under-screen camera. A recent optical detection technique, which relies on the retro-reflective effect of hidden cameras, is promising but is also greatly hindered by challenges introduced due to reflections from the screen that is placed in front of the under-screen camera. In this work, these challenges are addressed, by proposing a detection principle that exploits the difference in reflective nature between the USC and the screen. Using reflection detection in a sliding window approach, a detection methodology is given to detect the USC. Furthermore, a detection architecture is designed that incorporates the proposed detection principles using a combination of computer vision, image processing and machine learning techniques. Using an off-the-shelf Time-of-Flight sensor, this architecture is implemented into a detection system and evaluated on its robustness and detection accuracy. Experiments on a dataset of 200 videos with a variety of measurement conditions show that this detection system is capable of achieving a USC detection rate of 71.5% while having a false-positive rate of 21.5%. It also proves excellent results while the screen is displaying content.

Privacy concerns in federated learning have attracted considerable attention recently. In centralized networks, it has been observed that even without directly exchanging raw training data, the exchange of other so-called intermediate parameters such as weights/gradients can still potentially reveal private information. However, there has been relatively less research conducted on privacy concerns in decentralized networks.

In this report, we analyze privacy leakage in optimization-based decentralized federated learning, which adopts generally distributed optimization schemes such as ADMM or PDMM in federated learning. By combining local updates with global aggregations, it was proved that optimization-based approaches are more advantageous compared to the traditional average consensus-based approaches, especially in scenarios where the data at the nodes are not independent and identically distributed (non-IID).

We further extend the privacy bound in distributed optimization to the decentralized learning framework. Different from the fact in the centralized learning framework the leaked information is the local gradients of each individual participant at all rounds, we find that in decentralized cases the leaked information is the difference of the local gradients within a certain time interval. Motivated by the gradient inversion in centralized networks, we then design a homogeneous attack to iteratively optimize dummy data whose gradient differences are close to the true revealed gradient differences. Though the gradient difference information still brings privacy concerns, we show that it is more challenging for adversaries to reconstruct private data using the difference of gradients than using the gradients themselves in the centralized case.

To deal with the privacy attack, we propose several potential defense strategies such as early stopping, inexact update and quantization etc. The main advantage of these approaches is that they introduce error/noise/distortion into decentralized federated learning for protecting private information from being revealed to others without affecting the training accuracy. In addition, we also show that the larger the batchsize is, the more difficult for the adversary to reconstruct the private information.