Energy-Aware Dynamic Neural Inference

The growing demand for intelligent applications beyond the network edge, coupled with the need for sustainable operation, are driving the seamless integration of deep learning (DL) algorithms into energy-limited, and even energy-harvesting end-devices. However, the stochastic nature of ambient energy sources often results in insufficient harvesting rates, failing to meet the energy requirements for inference and causing significant performance degradation in energy-agnostic systems. To address this problem, we consider an on-device adaptive inference system equipped with an energy-harvester and finite-capacity energy storage. We then allow the device to reduce the run-time execution cost on-demand, by either switching between differently-sized neural networks, referred to as multi-model selection (MMS), or by enabling earlier predictions at intermediate layers, called early exiting (EE). The model to be employed, or the exit point is then dynamically chosen based on the energy storage and harvesting process states. We also study the efficacy of integrating the prediction confidence into the decision-making process. We derive a principled policy with theoretical guarantees for confidence-aware and -agnostic controllers. Moreover, in multi-exit networks, we study the advantages of taking decisions incrementally, exit-by-exit, by designing a lightweight reinforcement learning-based controller. Experimental results show that, as the rate of the ambient energy increases, energy- and confidence-aware control schemes show approximately 5% improvement in accuracy compared to their energy-aware confidence-agnostic counterparts. Incremental approaches achieve even higher accuracy, particularly when the energy storage capacity is limited relative to the energy consumption of the inference model.

Multi-stage Attack Detection and Prediction Using Graph Neural Networks: An IoT Feasibility Study

With the ever-increasing reliance on digital networks for various aspects of modern life, ensuring their security has become a critical challenge. Intrusion Detection Systems play a crucial role in ensuring network security, actively identifying and mitigating malicious behaviours. However, the relentless advancement of cyber-threats has rendered traditional/classical approaches insufficient in addressing the sophistication and complexity of attacks. This paper proposes a novel 3-stage intrusion detection system inspired by a simplified version of the Lockheed Martin cyber kill chain to detect advanced multi-step attacks. The proposed approach consists of three models, each responsible for detecting a group of attacks with common characteristics. The detection outcome of the first two stages is used to conduct a feasibility study on the possibility of predicting attacks in the third stage. Using the ToN IoT dataset, we achieved an average of 94% F1-Score among different stages, outperforming the benchmark approaches based on Random-forest model. Finally, we comment on the feasibility of this approach to be integrated in a real-world system and propose various possible future work.

Mitigating System Bias in Resource Constrained Asynchronous Federated Learning Systems

Federated learning (FL) systems face performance challenges in dealing with heterogeneous devices and non-identically distributed data across clients. We propose a dynamic global model aggregation method within Asynchronous Federated Learning (AFL) deployments to address these issues. Our aggregation method scores and adjusts the weighting of client model updates based on their upload frequency to accommodate differences in device capabilities. Additionally, we also immediately provide an updated global model to clients after they upload their local models to reduce idle time and improve training efficiency. We evaluate our approach within an AFL deployment consisting of 10 simulated clients with heterogeneous compute constraints and non-IID data. The simulation results, using the FashionMNIST dataset, demonstrate over 10% and 19% improvement in global model accuracy compared to state-of-the-art methods PAPAYA and FedAsync, respectively. Our dynamic aggregation method allows reliable global model training despite limiting client resources and statistical data heterogeneity. This improves robustness and scalability for real-world FL deployments.

FROST: Towards Energy-efficient AI-on-5G Platforms -- A GPU Power Capping Evaluation

The Open Radio Access Network (O-RAN) is a burgeoning market with projected growth in the upcoming years. RAN has the highest CAPEX impact on the network and, most importantly, consumes 73% of its total energy. That makes it an ideal target for optimisation through the integration of Machine Learning (ML). However, the energy consumption of ML is frequently overlooked in such ecosystems. Our work addresses this critical aspect by presenting FROST - Flexible Reconfiguration method with Online System Tuning - a solution for energy-aware ML pipelines that adhere to O-RAN's specifications and principles. FROST is capable of profiling the energy consumption of an ML pipeline and optimising the hardware accordingly, thereby limiting the power draw. Our findings indicate that FROST can achieve energy savings of up to 26.4% without compromising the model's accuracy or introducing significant time delays.

Federated Deep Learning for Intrusion Detection in IoT Networks

The vast increase of IoT technologies and the ever-evolving attack vectors and threat actors have increased cyber-security risks dramatically. Novel attacks can compromise IoT devices to gain access to sensitive data or control them to deploy further malicious activities. The detection of novel attacks often relies upon AI solutions. A common approach to implementing AI-based IDS in distributed IoT systems is in a centralised manner. However, this approach may violate data privacy and secrecy. In addition, centralised data collection prohibits the scale-up of IDSs. Therefore, intrusion detection solutions in IoT ecosystems need to move towards a decentralised direction. FL has attracted significant interest in recent years due to its ability to perform collaborative learning while preserving data confidentiality and locality. Nevertheless, most FL-based IDS for IoT systems are designed under unrealistic data distribution conditions. To that end, we design an experiment representative of the real world and evaluate the performance of two FL IDS implementations, one based on DNNs and another on our previous work on DBNs. For our experiments, we rely on TON-IoT, a realistic IoT network traffic dataset, associating each IP address with a single FL client. Additionally, we explore pre-training and investigate various aggregation methods to mitigate the impact of data heterogeneity. Lastly, we benchmark our approach against a centralised solution. The comparison shows that the heterogeneous nature of the data has a considerable negative impact on the model performance when trained in a distributed manner. However, in the case of a pre-trained initial global FL model, we demonstrate a performance improvement of over 20% (F1-score) when compared against a randomly initiated global model.

Sustainable Edge Intelligence Through Energy-Aware Early Exiting

Deep learning (DL) models have emerged as a promising solution for Internet of Things (IoT) applications. However, due to their computational complexity, DL models consume significant amounts of energy, which can rapidly drain the battery and compromise the performance of IoT devices. For sustainable operation, we consider an edge device with a rechargeable battery and energy harvesting (EH) capabilities. In addition to the stochastic nature of the ambient energy source, the harvesting rate is often insufficient to meet the inference energy requirements, leading to drastic performance degradation in energy-agnostic devices. To mitigate this problem, we propose energy-adaptive dynamic early exiting (EE) to enable efficient and accurate inference in an EH edge intelligence system. Our approach derives an energy-aware EE policy that determines the optimal amount of computational processing on a per-sample basis. The proposed policy balances the energy consumption to match the limited incoming energy and achieves continuous availability. Numerical results show that accuracy and service rate are improved up to 25% and 35%, respectively, in comparison with an energy-agnostic policy.

LE3D: A Lightweight Ensemble Framework of Data Drift Detectors for Resource-Constrained Devices

Data integrity becomes paramount as the number of Internet of Things (IoT) sensor deployments increases. Sensor data can be altered by benign causes or malicious actions. Mechanisms that detect drifts and irregularities can prevent disruptions and data bias in the state of an IoT application. This paper presents LE3D, an ensemble framework of data drift estimators capable of detecting abnormal sensor behaviours. Working collaboratively with surrounding IoT devices, the type of drift (natural/abnormal) can also be identified and reported to the end-user. The proposed framework is a lightweight and unsupervised implementation able to run on resource-constrained IoT devices. Our framework is also generalisable, adapting to new sensor streams and environments with minimal online reconfiguration. We compare our method against state-of-the-art ensemble data drift detection frameworks, evaluating both the real-world detection accuracy as well as the resource utilisation of the implementation. Experimenting with real-world data and emulated drifts, we show the effectiveness of our method, which achieves up to 97% of detection accuracy while requiring minimal resources to run.

A Federated Learning-enabled Smart Street Light Monitoring Application: Benefits and Future Challenges

Data-enabled cities are recently accelerated and enhanced with automated learning for improved Smart Cities applications. In the context of an Internet of Things (IoT) ecosystem, the data communication is frequently costly, inefficient, not scalable and lacks security. Federated Learning (FL) plays a pivotal role in providing privacy-preserving and communication efficient Machine Learning (ML) frameworks. In this paper we evaluate the feasibility of FL in the context of a Smart Cities Street Light Monitoring application. FL is evaluated against benchmarks of centralised and (fully) personalised machine learning techniques for the classification task of the lampposts operation. Incorporating FL in such a scenario shows minimal performance reduction in terms of the classification task, but huge improvements in the communication cost and the privacy preserving. These outcomes strengthen FL's viability and potential for IoT applications.

An Intrusion Detection System based on Deep Belief Networks

The rapid growth of connected devices has led to the proliferation of novel cyber-security threats known as zero-day attacks. Traditional behaviour-based IDS rely on DNN to detect these attacks. The quality of the dataset used to train the DNN plays a critical role in the detection performance, with underrepresented samples causing poor performances. In this paper, we develop and evaluate the performance of DBN on detecting cyber-attacks within a network of connected devices. The CICIDS2017 dataset was used to train and evaluate the performance of our proposed DBN approach. Several class balancing techniques were applied and evaluated. Lastly, we compare our approach against a conventional MLP model and the existing state-of-the-art. Our proposed DBN approach shows competitive and promising results, with significant performance improvement on the detection of attacks underrepresented in the training dataset.

A Dataset of Images of Public Streetlights with Operational Monitoring using Computer Vision Techniques

A dataset of street light images is presented. Our dataset consists of $\sim350\textrm{k}$ images, taken from 140 UMBRELLA nodes installed in the South Gloucestershire region in the UK. Each UMBRELLA node is installed on the pole of a lamppost and is equipped with a Raspberry Pi Camera Module v1 facing upwards towards the sky and lamppost light bulb. Each node collects an image at hourly intervals for 24h every day. The data collection spans for a period of six months. Each image taken is logged as a single entry in the dataset along with the Global Positioning System (GPS) coordinates of the lamppost. All entries in the dataset have been post-processed and labelled based on the operation of the lamppost, i.e., whether the lamppost is switched ON or OFF. The dataset can be used to train deep neural networks and generate pre-trained models providing feature representations for smart city CCTV applications, smart weather detection algorithms, or street infrastructure monitoring. The dataset can be found at \url{https://doi.org/10.5281/zenodo.6046758}.