Related papers: An adversarially robust data-market for spatial, c…

We propose using a hierarchical retail market structure to alert and dispatch resources to mitigate cyber-physical attacks on a distribution grid. We simulate attacks where a number of generation nodes in a distribution grid are attacked.…

We address the security of a network of Connected and Automated Vehicles (CAVs) cooperating to navigate through a conflict area. Adversarial attacks such as Sybil attacks can cause safety violations resulting in collisions and traffic jams.…

Data sharing is very important for accelerating scientific research, business innovations, and for informing individuals. Yet, concerns over data privacy, cost, and lack of secure data-sharing solutions have prevented data owners from…

This paper introduces Data Stations, a new data architecture that we are designing to tackle some of the most challenging data problems that we face today: access to sensitive data; data discovery and integration; and governance and…

Smart cities are data driven and collect data from a variety of sources. Certain types of data such as building data is under-represented and remains harder to find despite its value. Our goal is to incentivise the stakeholders to make…

Distributed control increases system scalability, flexibility, and redundancy. Foundational to such decentralisation is consensus formation, by which decision-making and coordination are achieved. However, decentralised multi-agent systems…

In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial attacks has been rarely explored. In this paper, we propose…

We study robust mean estimation in an online and distributed scenario in the presence of adversarial data attacks. At each time step, each agent in a network receives a potentially corrupted data point, where the data points were originally…

Distributed algorithms provide flexibility over centralized algorithms for resource allocation problems, e.g., cyber-physical systems. However, the distributed nature of these algorithms often makes the systems susceptible to…

We study virtual energy storage services based on the aggregation of EV batteries in parking lots under time-varying, uncertain EV departures and state-of-charge limits. We propose a convex data-driven scheduling framework in which a…

With the growing cyber-security threats, ensuring the security of data in Cloud data centers is a challenging task. A prominent type of attack on Cloud data centers is data tampering attack that can jeopardize the confidentiality and the…

Decentralized data-feed systems enable blockchain-based smart contracts to access off-chain information by aggregating values from multiple oracles. To improve accuracy, these systems typically use an aggregation function, such as majority…

Existing centralised market places such as Ebay enable companies to gather large amounts of personal data that can be used to manipulate users. Furthermore, users can frequently perform fraud without severe consequence. Reputation systems…

Machine Learning systems rely on data for training, input and ongoing feedback and validation. Data in the field can come from varied sources, often anonymous or unknown to the ultimate users of the data. Whenever data is sourced and used,…

In this paper, we consider the resilient multi-dimensional consensus and distributed optimization problems of multi-agent systems (MASs) in the presence of both agent-based and denial-of-service (DoS) attacks. The considered agent-based…

Smart contract-enabled blockchains allow building decentralized applications in which mutually-distrusted parties can work together. Recently, oracle services emerged to provide these applications with real-world data feeds. Unfortunately,…

Data poisoning is a threat model in which a malicious actor tampers with training data to manipulate outcomes at inference time. A variety of defenses against this threat model have been proposed, but each suffers from at least one of the…

DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in…

Decentralized machine learning often relies on outsourcing computations, such as gradient evaluations, to untrusted worker nodes. Existing robust aggregation methods can mitigate malicious behavior under honest-majority assumptions, but may…

Designing effective defense against adversarial attacks is a crucial topic as deep neural networks have been proliferated rapidly in many security-critical domains such as malware detection and self-driving cars. Conventional defense…