Admela Jukan

Sleman Mouammar, Thomas Röthig, Soheil Hosseini et al.

To enable efficient resource utilization under stringent Size, Weight, and Power (SWaP) constraints through transparent and all-optical switched satellites transmission, various switching paradigms can be considered, including packet, burst, or circuit. To this end, the traffic assembly and algorithmic design for path computations at the ground stations play a key role in determining the switching fabric design. Generally, traffic can be buffered and assembled in chunks at the ground stations and forwarded over the pre-computed optical path in space, similar to terrestrial optical burst switching or fast circuit switching. Regardless of the chosen paradigm, the switching fabric must satisfy specific latency performance requirements. This paper studies the performance of all-optical satellite networks based on the maximum traffic chunk sizes that can be scheduled and the performance of optical switching fabrics in the future over all-optical constellations. We consider various optical switching technologies, including MEMS- and integrated photonic-based solutions, in the context of switching speed, power consumption, and insertion loss. Simulation results indicate that traffic chunk size critically impacts the performance required by optical switching fabrics onboard a satellite.

Iulisloi Zacarias, Marla Grunewald, Fin Gentzen et al.

In the EU project MARE, a novel plane was proposed and used in combination with intent-based networking (IBN), allowing the operator to focus on what, rather than on how. Recently, LLMs have been successfully employed to translate the high-level intents into low-level actions. The open challenge is to understand how IBN can be effectively enhanced with LLM and the emerging agentic AI for security purposes. Enhancing IBN with an agentic AI paradigm introduces significant challenges that existing solutions do not fully address. This paper proposes an enhanced IBN framework with a strong security focus toward agentic AI. We address the architectural and security requirements for a multi-agent intent-based system (IBS) architecture, including a multi-domain IBN. We propose a hierarchical multi-agent and multi-vendor architecture that can also be applied more broadly in 6G architectures and beyond, beyond the security architecture proposed in MARE. The architecture incorporates an interactive intent-processing pipeline using LLMs, and it also allows the IBS to connect to external security knowledge bases, such as MITRE ATT\&CK, MITRE FiGHT, and NIST.

Marla Grunewald, Mounir Bensalem, Admela Jukan

We propose to integrate long-distance LongRange (LoRa) communication solution for sending the data from IoT to the edge computing system, by taking advantage of its unlicensed nature and the potential for open source implementations that are common in edge computing. We propose a channel hoping optimization model and apply TinyML-based channel hoping model based for LoRa transmissions, as well as experimentally study a fast predictive algorithm to find free channels between edge and IoT devices. In the open source experimental setup that includes LoRa, TinyML and IoT-edge-cloud continuum, we integrate a novel application workflow and cloud-friendly protocol solutions in a case study of plant recommender application that combines concepts of microfarming and urban computing. In a LoRa-optimized edge computing setup, we engineer the application workflow, and apply collaborative filtering and various machine learning algorithms on application data collected to identify and recommend the planting schedule for a specific microfarm in an urban area. In the LoRa experiments, we measure the occurrence of packet loss, RSSI, and SNR, using a random channel hoping scheme to compare with our proposed TinyML method. The results show that it is feasible to use TinyML in microcontrollers for channel hopping, while proving the effectiveness of TinyML in learning to predict the best channel to select for LoRa transmission, and by improving the RSSI by up to 63 %, SNR by up to 44 % in comparison with a random hopping mechanism.

Cao-Vien Phung, Thomas Röthig, Admela Jukan

Low Earth Orbit (LEO) satellite networks are increasingly adopting laser (Free Space Optics, FSO) links to provide high-capacity communications. Although laser inter-satellite links offer high throughput and low latency, RF up- and downlinks remain necessary to maintain connectivity during optical outages caused by adverse atmospheric conditions. In such hybrid link scenarios, satellite buffer design remains a key challenge, since up- and downlink traffic must be buffered and forwarded among satellite nodes. The hybrid RF/FSO scenario requires careful transmission scheduling, especially at envisioned optical transmission rates of 100Gb/s and beyond, making buffer sizing critical under strict onboard energy and weight constraints. Thus, this paper analyzes throughput performance and buffer sizing in hybrid RF/laser satellite networks with finite buffer capacity, interference-aware scheduling, and weather-dependent laser link outage probabilities. Numerical results indicate that laser communications bring significant performance gains. Instead of increasing the transmission power of the satellite to maximize the throughput, we can select a suitable transmission scheduling priority to achieve a maximum throughput, while minimizing the buffer requirement, and lowering packet loss probability under realistic operational conditions and constraints.

Zied Jenhani, Mounir Bensalem, Jasenka Dizdarević et al.

Running deep learning inference directly on ultra-low-power edge/IoT nodes has been limited by the tight memory and compute budgets of microcontrollers. Split learning (SL) addresses this limitation in which it executes part of the inference process on the sensor and off-loads the remainder to a companion device. In the context of constrained devices and the related impact of low-power, over-the-air transport protocols, the performance of split learning remains largely unexplored. TO the best of our knowledge, this paper presents the first end-to-end TinyML + SL testbed built on Espressif ESP32-S3 boards, designed to benchmark the over-the-air performance of split learning TinyML in edge/IoT environments. We benchmark the performance of a MobileNetV2 image recognition model, which is quantized to 8-bit integers, partitioned, and delivered to the nodes via over-the-air updates. The intermediate activations are exchanged through different wireless communication methods: ESP-NOW, BLE, and traditional UDP/IP and TCP/IP, enabling a head-to-head comparison on identical hardware. Measurements show that splitting the model after block_16_project_BN layer generates a 5.66 kB tensor that traverses the link in 3.2 ms, when UDP is used, achieving a steady-state round-trip latency of 5.8 s. ESP-NOW presents the most favorable RTT performance 3.7 s; BLE extends battery life further but increases latency beyond 10s.

Fin Gentzen, Mounir Bensalem, Admela Jukan

Machine learning (ML) models, data and software need to be regularly updated whenever essential version updates are released and feasible for integration. This is a basic but most challenging requirement to satisfy in the edge, due to the various system constraints and the major impact that an update can have on robustness and stability. In this paper, we formulate for the first time the ML model versioning optimization problem, and propose effective solutions, including the update automation with reinforcement learning (RL) based algorithm. We study the edge network environment due to the known constraints in performance, response time, security, and reliability, which make updates especially challenging. The performance study shows that model version updates can be fully and effectively automated with reinforcement learning method. We show that for every range of server load values, the proper versioning can be found that improves security, reliability and/or ML model accuracy, while assuring a comparably lower response time.

Anna Engelmann, Admela Jukan

Anonymity networks are providing practical mechanisms to protect its users against censorship by hiding their identity and information content. The best-known anonymity network, The Onion Routing (Tor) network, is however subject to censorship attacks by blocking the public Tor entry routers and a few secret Tor entry points (bridges), thus preventing users to access the Tor. To further advance the evolution of anonymity networks, while addressing censorship attacks, we propose to enhance the well-known multi-circuit Tor technique with linear network coding (LNC) and analyze the resulting censorship success. The results show that LNC can improve the robustness of Tor against censorship.

Javier Mata, Ignacio de Miguel, Ramó n J. Durá n et al.

Artificial intelligence (AI) is an extensive scientific discipline which enables computer systems to solve problems by emulating complex biological processes such as learning, reasoning and self-correction. This paper presents a comprehensive review of the application of AI techniques for improving performance of optical communication systems and networks. The use of AI-based techniques is first studied in applications related to optical transmission, ranging from the characterization and operation of network components to performance monitoring, mitigation of nonlinearities, and quality of transmission estimation. Then, applications related to optical network control and management are also reviewed, including topics like optical network planning and operation in both transport and access networks. Finally, the paper also presents a summary of opportunities and challenges in optical networking where AI is expected to play a key role in the near future.

Anna Engelmann, Admela Jukan

Privacy in form of anonymous communication could be comparably both faster and harder to break in optical routers than in today's anonymous IP networks based on The Onion Routing (Tor). Implementing the practical privacy alloptically,however, is not straightforward, as it requires key generation in each anonymization node to avoid distribution of long keys, and layered encryption, both at the optical line rate. Due to the unavailability of cryptographically strong optical key generation and encryption components, not only a layered encryption is a challenge, but an optical encryption in general. In this paper, we address the challenges of optical anonymous networking for the first time from the system's perspective, and discuss options for practical implementation of all-optical layered encryption. To this end, we propose an optical anonymization component realized with the state-of-the-art optical XOR logic and optical Linear Feedback Shift Registers (oLFSRs). Given that LFSR alone is known for its weak cryptographic security due to its linear properties, we propose an implementation with parallel oLFSRs and analyze the resulting computational security. The results show that proposed optical anonymization component is promising as it can be practically realized to provide a high computational security against deanonymization (privacy) attack.

Anna Engelmann, Admela Jukan

We propose a novel system for optical encryption based on an optical XOR and optical Linear Feedback Shift Register (oLFSRs). Though we choose LFSR for its ability to process optical signals at line rate, we consider the fact that it offers no cryptographic security. To address the security shortfall, we propose implementation of parallel oLFSRs, whereby the resulting key-stream at line rate is controlled electronically by a nonlinear random number generator at speeds much lower than the optical line rate, which makes the system practically relevant. The analysis of computational security shows that the proposed system is secure against wiretapping and can be engineered with the state of the art optical components.

Anna Engelmann, Admela Jukan

As more and more data is transmitted in the configurable optical layer, whereby all optical switches forward packets without electronic layers involved, we envision privacy as the intrinsic property of future optical networks. In this paper, we propose Optical Onion Routing (OOR) routing and forwarding techniques, inspired by the onion routing in the Internet layer, the best known realization of anonymous communication today, but designed with specific features innate to optical networks. We propose to design the optical anonymization network system with a new optical anonymization node architecture, including the optical components and their electronic counterparts to realize layered encryption. We propose modification to the secret key generation using Linear Feedback Shift Register (LFSR), able to utilize different primitive irreducible polynomials, and the usage optical XOR operation as encryption, an important optical technology coming of age. We prove formally that, for the proposed encryption techniques and distribution of secret information, the optical onion network is perfectly private and secure. The paper aims at providing practical foundations for privacy-enhancing optical network technologies.

Anna Engelmann, Admela Jukan

Recently, physical layer security in the optical layer has gained significant traction. Security treats in optical networks generally impact the reliability of optical transmission. Linear Network Coding (LNC) can protect from both the security treats in form of eavesdropping and faulty transmission due to jamming. LNC can mix original data to become incomprehensible for an attacker and also extend original data by coding redundancy, thus protecting a data from errors injected via jamming attacks. In this paper, we study the effectiveness of LNC to balance reliable transmission and security in optical networks. To this end, we combine the coding process with data flow parallelization of the source and propose and compare optimal and randomized path selection methods for parallel transmission. The study shows that a combination of data parallelization, LNC and randomization of path selection increases security and reliability of the transmission. We analyze the so-called catastrophic security treat of the network and show that in case of conventional transmission scheme and in absence of LNC, an attacker could eavesdrop or disrupt a whole secret data by accessing only one edge in a network.