Amin Hassanzadeh

Minxue Tang, Jianyi Zhang, Mingyuan Ma et al.

Federated adversarial training can effectively complement adversarial robustness into the privacy-preserving federated learning systems. However, the high demand for memory capacity and computing power makes large-scale federated adversarial training infeasible on resource-constrained edge devices. Few previous studies in federated adversarial training have tried to tackle both memory and computational constraints simultaneously. In this paper, we propose a new framework named Federated Adversarial Decoupled Learning (FADE) to enable AT on heterogeneous resource-constrained edge devices. FADE differentially decouples the entire model into small modules to fit into the resource budget of each device, and each device only needs to perform AT on a single module in each communication round. We also propose an auxiliary weight decay to alleviate objective inconsistency and achieve better accuracy-robustness balance in FADE. FADE offers theoretical guarantees for convergence and adversarial robustness, and our experimental results show that FADE can significantly reduce the consumption of memory and computing power while maintaining accuracy and robustness.

Jingwei Sun, Ang Li, Louis DiValentin et al.

Federated learning (FL) is a popular distributed learning framework that trains a global model through iterative communications between a central server and edge devices. Recent works have demonstrated that FL is vulnerable to model poisoning attacks. Several server-based defense approaches (e.g. robust aggregation), have been proposed to mitigate such attacks. However, we empirically show that under extremely strong attacks, these defensive methods fail to guarantee the robustness of FL. More importantly, we observe that as long as the global model is polluted, the impact of attacks on the global model will remain in subsequent rounds even if there are no subsequent attacks. In this work, we propose a client-based defense, named White Blood Cell for Federated Learning (FL-WBC), which can mitigate model poisoning attacks that have already polluted the global model. The key idea of FL-WBC is to identify the parameter space where long-lasting attack effect on parameters resides and perturb that space during local training. Furthermore, we derive a certified robustness guarantee against model poisoning attacks and a convergence guarantee to FedAvg after applying our FL-WBC. We conduct experiments on FasionMNIST and CIFAR10 to evaluate the defense against state-of-the-art model poisoning attacks. The results demonstrate that our method can effectively mitigate model poisoning attack impact on the global model within 5 communication rounds with nearly no accuracy drop under both IID and Non-IID settings. Our defense is also complementary to existing server-based robust aggregation approaches and can further improve the robustness of FL under extremely strong attacks.

Nader Sehatbakhsh, Ellie Daw, Onur Savas et al.

As machine learning becomes a more mainstream technology, the objective for governments and public sectors is to harness the power of machine learning to advance their mission by revolutionizing public services. Motivational government use cases require special considerations for implementation given the significance of the services they provide. Not only will these applications be deployed in a potentially hostile environment that necessitates protective mechanisms, but they are also subject to government transparency and accountability initiatives which further complicates such protections. In this paper, we describe how the inevitable interactions between a user of unknown trustworthiness and the machine learning models, deployed in governments and public sectors, can jeopardize the system in two major ways: by compromising the integrity or by violating the privacy. We then briefly overview the possible attacks and defense scenarios, and finally, propose recommendations and guidelines that once considered can enhance the security and privacy of the provided services.

Amin Hassanzadeh, Amin Rasekh, Stefano Galelli et al.

This study presents a critical review of disclosed, documented, and malicious cybersecurity incidents in the water sector to inform safeguarding efforts against cybersecurity threats. The review is presented within a technical context of industrial control system architectures, attack-defense models, and security solutions. Fifteen incidents were selected and analyzed through a search strategy that included a variety of public information sources ranging from federal investigation reports to scientific papers. For each individual incident, the situation, response, remediation, and lessons learned were compiled and described. The findings of this review indicate an increase in the frequency, diversity, and complexity of cyberthreats to the water sector. Although the emergence of new threats, such as ransomware or cryptojacking, was found, a recurrence of similar vulnerabilities and threats, such as insider threats, was also evident, emphasizing the need for an adaptive, cooperative, and comprehensive approach to water cyberdefense.