Artificial Intelligence used in future networks is vulnerable to biases, misclassifications, and security threats, which seeds constant scrutiny in accountability. Explainable AI (XAI) methods bridge this gap in identifying unaccounted biases in black-box AI/ML models. However, scaffolding attacks can hide the internal biases of the model from XAI methods, jeopardizing any auditory or monitoring processes, service provisions, security systems, regulators, auditors, and end-users in future networking paradigms, including Intent-Based Networking (IBN). For the first time ever, we formalize and demonstrate a framework on how an attacker would adopt scaffoldings to deceive the security auditors in Network Intrusion Detection Systems (NIDS). Furthermore, we propose a detection method that auditors can use to detect the attack efficiently. We rigorously test the attack and detection methods using the NSL-KDD. We then simulate the attack on 5G network data. Our simulation illustrates that the attack adoption method is successful, and the detection method can identify an affected model with extremely high confidence.

Despite its enormous economical and societal impact, lack of human-perceived control and safety is re-defining the design and development of emerging AI-based technologies. New regulatory requirements mandate increased human control and oversight of AI, transforming the development practices and responsibilities of individuals interacting with AI. In this paper, we present the SPATIAL architecture, a system that augments modern applications with capabilities to gauge and monitor trustworthy properties of AI inference capabilities. To design SPATIAL, we first explore the evolution of modern system architectures and how AI components and pipelines are integrated. With this information, we then develop a proof-of- concept architecture that analyzes AI models in a human-in-the- loop manner. SPATIAL provides an AI dashboard for allowing individuals interacting with applications to obtain quantifiable insights about the AI decision process. This information is then used by human operators to comprehend possible issues that influence the performance of AI models and adjust or counter them. Through rigorous benchmarks and experiments in real- world industrial applications, we demonstrate that SPATIAL can easily augment modern applications with metrics to gauge and monitor trustworthiness, however, this in turn increases the complexity of developing and maintaining systems implementing AI. Our work highlights lessons learned and experiences from augmenting modern applications with mechanisms that support regulatory compliance of AI. In addition, we also present a road map of on-going challenges that require attention to achieve robust trustworthy analysis of AI and greater engagement of human oversight.

With the rapid progression of communication and localisation of big data over billions of devices, distributed Machine Learning (ML) techniques are emerging to cater for the development of Artificial Intelligence (AI)-based services in a distributed manner. Federated Learning (FL) is such an innovative approach to achieve a privacy-preserved AI that facilitates ML model sharing and aggregation while keeping the participants’ data at the original source. However, recent research has investigated threats from poisoning attacks in FL. Several robust algorithms based on techniques such as similarity metrics or anomaly filtering are proposed as solutions. Yet, these approaches do not focus on investigating the intentions of the attackers or providing justifications and evidence for suspecting the behaviour of clients who are considered poisoners. Therefore, we propose SHERPA, a robust algorithm that uses Shapley Additive Explanations (SHAP) to identify potential poisoners in an FL system. Based on this, we develop a novel algorithm to differentiate poisoners via feature attribution clustering. We launch data poisoning attacks for different scenarios on multiple datasets and showcase our solution to mitigate the attacks. Furthermore, we show that privacy-targeted poisoning attacks can be mitigated with our approach. Accompanying the Explainable AI (XAI) technique for defence, our study reveals the potential for post-hoc feature attributions in countering data poisoning attacks with better explainability and improved justification in eliminating potentially malicious clients in the aggregation process.

Federated Learning (FL) is an emerging privacy-preserved distributed Machine Learning (ML) technique where multiple clients can contribute to training an ML model without sharing private data. Even though FL offers a certain level of privacy by design, recent works show that FL is vulnerable to numerous privacy attacks. One of the key features of FL is the continuous training of FL models over many cycles through time. Observing changes in FL models over time can lead to inferring information on changes to private and sensitive data used in the FL process. However, this potential leakage of private information is not yet investigated significantly. Therefore, this paper introduces a new form of inference-based privacy attacks called FL Time Inference Attacks (FL-TIA). These attacks can reveal private time-related properties such as the presence or absence of a sensitive feature over time and if it is periodical. We consider two forms of such FL-TIA: i.e. identifying changes in membership of target data records over training rounds and detecting significant events in clients over time by observing differences in FL models. We use the network Intrusion Detection System (IDS) as a use case to demonstrate the impact of our attack. We propose a continuous updating attack model method for membership variation detection by sustaining the accuracy of the attack. Furthermore, we provide an efficient detection method that can identify model changes using cosine similarity metric and one-shot mapping on shadow model training.

The global view enabled by a Software Defined Network (SDN) architecture allows us to observe the contribution of each congested router to the overall Mean Opinion Score (MOS) degradation of a VoIP service. Thus, when a number of routers in the path may add to the MOS degradation, the SDN controller can quantify the contribution from each router. This work presents the implementation of a network monitoring system for OpenFlow protocol aware enterprise VoIP networks. The presented solution enables network administrators and developers to access on demand information about intermediate packet loss and MOS for real-time applications. The main contribution of this work is an out-of-the-box architecture to enable users to find the exact location of quality degradation with a small operational cost.

The Software Defined Networking (SDN) paradigm enables quick deployment of software controlled network infrastructures, however new approaches to system monitoring are required to provide network administrators with instant feedback on a network's health. This paper details the deployment of an SDN system architecture featuring the integration of a cloud-based, real-time log-analysis platform. The proposed architecture uses log data collected from host machines, OpenFlow switches and the SDN controllers in a non-invasive style. This work uses a commercially available correlation platform to provide network administrators with a real-time view of the network status and the approach is validated under two scenarios:network overload and a security attack.