Search for: All records

This artifact provides a machine learning–based toolkit for detecting Fake Base Stations (FBS) and Multi-Step Attacks (MSAs) in cellular networks from network traces in the UE. It includes curated layer-3 cellular network traces (NAS/RRC) along with scripts for preprocessing, model training, evaluation, cross-validation, and performance visualization. Users can easily experiment with a variety of classification approaches—including Random Forest, Support Vector Machines, XGBoost, CNN, LSTM, and Graph Neural Network—by running the provided Python scripts. Metrics such as accuracy, precision, recall, and F1-score are automatically calculated, and visual outputs are generated for further analysis. Beyond classical ML models, the repository also contains scripts for graph-based models (GCN, GAT, GATv2, GraphSAGE, Graph Transformer) and a stateful LSTM with attention. These scripts demonstrate how sequential data (e.g., NAS/RRC messages) and structured data (e.g., graphs of packet traces) can be leveraged for attack detection. Additional scripts (e.g., cross-validation, trace-level classification, and feature extraction) further streamline the ML workflow. While the repository includes our implementation of a signature-based detection approach for comparison, the main focus is on training and evaluating data-driven ML models to showcase their effectiveness in detecting FBSes and MSAs from cellular network traffic. 

Cyber-Physical Systems (CPS) integrate computing, networking, and physical processes, making them critical in applications such as smart homes, industrial control systems, autonomous vehicles, smart grids, and medical devices. Ensuring CPS security is essential, as vulnerabilities can have serious consequences. CPS share key security requirements with traditional IT systems-confidentiality, integrity, and availability-but also introduce additional challenges due to real-time constraints, interactions with physical processes, and safety considerations. Standard security practices include secure design principles, redundancy, continuous monitoring, resilient control algorithms, and rigorous verification and validation procedures. However, security techniques must be tailored to specific CPS domains. Some of the requirements may interact with each other, e.g., adding security mechanisms violating timely responses, or lack of security measures impacting safety. The complexity of securing CPS is further heightened by the integration of artificial intelligence (AI), which enables greater system autonomy in tasks like energy optimization and security monitoring. In this paper, we present results from two previous projects that focused on smart IoT systems and avionic systems, respectively. In both cases, arriving at solutions that combine many requirements is at the heart of the methodology. Based on this past work, we discuss open research directions. 

Intrusion detection systems (IDSes) are critical building blocks for securing Internet-of-Things (IoT) devices and networks. Advances in AI techniques are contributing to enhancing the efficiency of IDSes, but their performance typically depends on high-quality training datasets. The scarcity of such datasets is a major concern for the effective use of machine learning for IDSes in IoT networks. To address such a need, we present IoTDSCreator - a tool for the automatic generation of labeled datasets able to support various devices, connectivity technologies, and attacks. IoTDSCreator provides a user with DC-API, an API by which the user can describe a target network and an attack scenario against it. Based on the description, the framework configures the network, leveraging virtualization techniques on user-provided physical machines, performs single or multi-step attacks, and finally returns labeled datasets. Thereby, IoTDSCreator dramatically reduces the manual effort for generating labeled and diverse datasets. We release the source code of IoTDSCreator and 16 generated datasets with 193 features based on 26 types of IoT devices, 2 types of communication links, and 15 types of IoT applications. 

Federated learning (FL) is well-suited to 5G networks, where many mobile devices generate sensitive edge data. Secure aggregation protocols enhance privacy in FL by ensuring that individual user updates reveal no information about the underlying client data. However, the dynamic and large-scale nature of 5G-marked by high mobility and frequent dropouts-poses significant challenges to the effective adoption of these protocols. Existing protocols often require multi-round communication or rely on fixed infrastructure, limiting their practicality. We propose a lightweight, single-round secure aggregation protocol designed for 5G environments. By leveraging base stations for assisted computation and incorporating precomputation, key-homomorphic pseudorandom functions, and t-out-of-k secret sharing, our protocol ensures efficiency, robustness, and privacy. Experiments show strong security guarantees and significant gains in communication and computation efficiency, making the approach well-suited for real-world 5G FL deployments. 

In applying deep learning for malware classifica- tion, it is crucial to account for the prevalence of malware evolution, which can cause trained classifiers to fail on drifted malware. Existing solutions to address concept drift use active learning. They select new samples for analysts to label and then retrain the classifier with the new labels. Our key finding is that the current retraining techniques do not achieve optimal results. These techniques overlook that updating the model with scarce drifted samples requires learning features that remain consistent across pre-drift and post-drift data. The model should thus be able to disregard specific features that, while beneficial for the classification of pre-drift data, are absent in post-drift data, thereby preventing prediction degradation. In this paper, we propose a new technique for detecting and classifying drifted malware that learns drift-invariant features in malware control flow graphs by leveraging graph neural networks with adversarial domain adaptation. We compare it with existing model retraining methods in active learning-based malware detection systems and other domain adaptation techniques from the vision domain. Our approach significantly improves drifted malware detection on publicly available benchmarks and real-world malware databases reported daily by security companies in 2024. We also tested our approach in predicting multiple malware families drifted over time. A thorough evaluation shows that our approach outperforms the state-of-the-art approaches. 

Not AvailableDisaggregated computer architectures are an interesting paradigm according to which the components of a traditional monolithic server, such as CPU, memory, storage, and networking, are separated into distinct, often independently managed units that communicate over a network. Disaggregation not only offers benefits such as greater flexibility, scalability, and resource optimization but can also improve security. For example, in the context of enterprise routing, it can offer fine-grained control over the network that allows one to deploy security policies, access control rules, and threat detection mechanisms more precisely, ensuring that only authorized traffic flows through the enterprise environment. It makes patch management easier because its modularity allows different components to be patched independently. The same benefits also apply to cellular networks. Disaggregation is a key feature of the Open Radio Access Network (O-RAN) paradigm, whose goal is to make the radio access network intelligent, virtualized, and fully interoperable. However, disaggregation also introduces several unique security risks, such as increased attack surfaces, increased exposure of sensitive data, increased difficulty in tracing data provenance, insecure isolation among different components, and insecure APIs. In addition, well-known security technologies, such as trusted execution environments, may have to be redesigned in the context of disaggregated architectures. In this paper, after an overview of these benefits and concerns, we focus on the research approaches proposed to address some of these concerns for network fabric, O-RAN, and trusted execution environments. 

Zero Trust (ZT) is a security paradigm aiming to curtail an attacker’s lateral movements within a network by implementing least-privilege and per-request access control policies. However, its widespread adoption is hindered by the difficulty of generating proper rules owing to the lack of detailed knowledge of communication requirements and the characteristic behaviors of communicating entities under benign conditions. Consequently, manual rule generation becomes cumbersome and error prone. To address these problems, we proposeZT-SDN, an automated framework for learning and enforcing network access control in Software-Defined Networks (SDNs). ZT-SDN collects data from the underlying network and models the network “transactions” performed by communicating entities as graphs. The nodes represent entities, whereas the directed edges represent transactions identified by different protocol stacks observed. It uses novel unsupervised learning approaches to extract transaction patterns directly from the network data, such as the allowed protocol stacks and port numbers and data transmission behavior. Finally, ZT-SDN uses an innovative approach to generate correct access control rules and infer strong associations between them, allowing proactive rule deployment in forwarding devices. We show the framework’s efficacy in detecting abnormal network accesses and abuses of permitted flows in changing network conditions with real network datasets. Additionally, we showcase ZT-SDN’s scalability and the network’s performance when applied in an SDN environment. 

Federated learning (FL) enables collaborative model training while preserving user data privacy by keeping data local. Despite these advantages, FL remains vulnerable to privacy attacks on user updates and model parameters during training and deployment. Secure aggregation protocols have been proposed to protect user updates by encrypting them, but these methods often incur high computational costs and are not resistant to quantum computers. Additionally, differential privacy (DP) has been used to mitigate privacy leakages, but existing methods focus on secure aggregation or DP, neglecting their potential synergies. To address these gaps, we introduce Beskar, a novel framework that provides post-quantum secure aggregation, optimizes computational overhead for FL settings, and defines a comprehensive threat model that accounts for a wide spectrum of adversaries. We also integrate DP into different stages of FL training to enhance privacy protection in diverse scenarios. Our framework provides a detailed analysis of the trade-offs between security, performance, and model accuracy, representing the first thorough examination of secure aggregation protocols combined with various DP approaches for post-quantum secure FL. Beskar aims to address the pressing privacy and security issues FL while ensuring quantum-safety and robust performance. 

The rampant occurrence of cybersecurity breaches imposes substantial limitations on the progress of network infras- tructures, leading to compromised data, financial losses, potential harm to individuals, and disruptions in essential services. The current security landscape demands the urgent development of a holistic security assessment solution that encompasses vul- nerability analysis and investigates the potential exploitation of these vulnerabilities as attack paths. In this paper, we propose GRAPHENE, an advanced system designed to provide a detailed analysis of the security posture of computing infrastructures. Using user-provided information, such as device details and software versions, GRAPHENE performs a comprehensive secu- rity assessment. This assessment includes identifying associated vulnerabilities and constructing potential attack graphs that adversaries can exploit. Furthermore, it evaluates the exploitabil- ity of these attack paths and quantifies the overall security posture through a scoring mechanism. The system takes a holistic approach by analyzing security layers encompassing hardware, system, network, and cryptography. Furthermore, GRAPHENE delves into the interconnections between these layers, exploring how vulnerabilities in one layer can be leveraged to exploit vulnerabilities in others. In this paper, we present the end-to-end pipeline implemented in GRAPHENE, showcasing the systematic approach adopted for conducting this thorough security analysis.