Develo** future human-centered smart cities: Critical analysis of smart city security, Data management, and Ethical challenges
As the globally increasing population drives rapid urbanization in various parts of the world,
there is a great need to deliberate on the future of the cities worth living. In particular, as …
there is a great need to deliberate on the future of the cities worth living. In particular, as …
Privacy and robustness in federated learning: Attacks and defenses
As data are increasingly being stored in different silos and societies becoming more aware
of data privacy issues, the traditional centralized training of artificial intelligence (AI) models …
of data privacy issues, the traditional centralized training of artificial intelligence (AI) models …
Security and privacy in the emerging cyber-physical world: A survey
With the emergence of low-cost smart and connected IoT devices, the area of cyber-physical
security is becoming increasingly important. Past research has demonstrated new threat …
security is becoming increasingly important. Past research has demonstrated new threat …
De-pois: An attack-agnostic defense against data poisoning attacks
Machine learning techniques have been widely applied to various applications. However,
they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can …
they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can …
Deep reinforcement learning for partially observable data poisoning attack in crowdsensing systems
M Li, Y Sun, H Lu, S Maharjan… - IEEE Internet of Things …, 2019 - ieeexplore.ieee.org
Crowdsensing systems collect various types of data from sensors embedded on mobile
devices owned by individuals. These individuals are commonly referred to as workers that …
devices owned by individuals. These individuals are commonly referred to as workers that …
Revisiting adversarially learned injection attacks against recommender systems
Recommender systems play an important role in modern information and e-commerce
applications. While increasing research is dedicated to improving the relevance and …
applications. While increasing research is dedicated to improving the relevance and …
Aflguard: Byzantine-robust asynchronous federated learning
Federated learning (FL) is an emerging machine learning paradigm, in which clients jointly
learn a model with the help of a cloud server. A fundamental challenge of FL is that the …
learn a model with the help of a cloud server. A fundamental challenge of FL is that the …
Towards understanding and enhancing robustness of deep learning models against malicious unlearning attacks
Given the availability of abundant data, deep learning models have been advanced and
become ubiquitous in the past decade. In practice, due to many different reasons (eg …
become ubiquitous in the past decade. In practice, due to many different reasons (eg …
Ml attack models: adversarial attacks and data poisoning attacks
J Lin, L Dang, M Rahouti, K **ong - arxiv preprint arxiv:2112.02797, 2021 - arxiv.org
Many state-of-the-art ML models have outperformed humans in various tasks such as image
classification. With such outstanding performance, ML models are widely used today …
classification. With such outstanding performance, ML models are widely used today …
Analysis of label-flip poisoning attack on machine learning based malware detector
With the increase in machine learning (ML) applications in different domains, incentives for
deceiving these models have reached more than ever. As data is the core backbone of ML …
deceiving these models have reached more than ever. As data is the core backbone of ML …