Towards intelligent security mechanisms for connected things

• Ano de defesa: 2023
• Autor(a) principal: ARAUJO FILHO, Paulo Freitas de
• Orientador(a): CAMPELO, Divanilson R.
• Tipo de documento: Tese
• Tipo de acesso: Acesso embargado
• Idioma: por
• Instituição de defesa: Universidade Federal de Pernambuco
• Programa de Pós-Graduação: Programa de Pos Graduacao em Ciencia da Computacao
• País: Brasil
• Palavras-chave em Português: Redes de computadores; Internet das coisas; Aprendizagem de máquina
• Link de acesso: https://repositorio.ufpe.br/handle/123456789/49599

The broadcast nature of wireless communications and the widespread adoption of connected things increase attack surfaces and enable attackers to launch several cyber-attacks. Moreover, the increasing adoption of machine learning (ML) in many applications, including wireless communications, introduces new risks and vulnerabilities. Adversarial attacks craft and introduce small perturbations that fool ML models into making wrong decisions. Hence, they may compromise wireless communications tasks based on ML and jeopardize communication availability and connected objects’ security. Therefore, cyber-attacks and adversarial attacks may compromise security goals, causing severe damage and financial losses and even putting people’s lives at risk. In this thesis, we advance the state-of-the-art in the security field by considering both the cyber-attacks and adversarial attacks problems. We enhance the security of connected objects by effectively and efficiently detecting cyber-attacks while defending systems that rely on machine learning from adversarial attacks. In Chapter 3, we verify that although unsupervised ML-based intrusion detection systems (IDSs) are necessary due to the difficulty and cost of obtaining labeled data, they usually present high false positive rates and long detection times. Thus, we propose a novel unsupervised IDS that detects known and unknown attacks using generative adversarial networks (GANs). Our approach combines the GAN discrimination and reconstruction losses, and uses an encoder neural network that accelerates the reconstruction loss computation, significantly reducing detection times compared to state-of-the-art approaches. Since many attacks have multiple steps and are launched from different applications and devices, Chapter 4 concerns different strategies for considering time dependencies among data in the detection of cyber-attacks. We propose a novel unsupervised GAN-Based IDS that uses temporal convolutional networks (TCNs) and self-attention to replace LSTM networks for considering time dependencies among data. Our proposed approach successfully replaces LSTM networks for attack detection and achieves better detection results. Moreover, it allows different configurations of TCN and self-attention layers to achieve different trade-offs between detection rates and detection times and satisfy different requirements. In Chapter 5, we verify that the existing adversarial attack techniques either require complete knowledge about the classifier’s model, which is an unrealistic assumption, or take too long to craft adversarial perturbations, such that they cannot tamper with modulated signals received by wireless receivers. Thus, we propose a novel black-box adversarial attack technique that reduces the accuracy of modulation classifiers more than other black-box adversarial attacks and crafts adversarial perturbations significantly faster than them. Our proposed technique is essential for assessing the risks of using machine learning-based modulation classifiers in wireless communications. Finally, given the damage that adversarial attacks may cause and the ineffectiveness of the existing defense techniques, in Chapter 6, we propose a defense technique for protecting modulation classifiers from adversarial attacks so that those attacks do not harm the availability of wireless communications. Our proposed approach detects and removes adversarial perturbations while reducing the sensitivity of machine learning-based classifiers to them. Hence, it successfully diminishes the accuracy reduction caused by different adversarial attack techniques.