In this talk, I will briefly introduce some of my previous and ongoing security and privacy research projects. I will then focus on one of these projects: multiparty privacy. Privacy is not just about what an individual user discloses about herself, it also involves what others (e.g. her friends) may disclose about her. Multiparty privacy is concerned with information pertaining to several individuals and the conflicts that arise when the privacy preferences of these individuals differ. In particular, I will go through the research we have been doing on multiparty privacy applied to social media and the future challenges in general in this field.

As geopolitics and technological developments collide and interact more and more, the involvement of governemnts, industry and civil society in decision making and the shaping of digital diplomacy is growing ever more relevant. The traditional models of governance and state to state interactions have been disrupted by the digital age and we now face the challenge of who is leading, who is following and who is left behind. The digital world connects every aspect of our public infrastructure and private lives. However, the same networks that bind people together also place our connected society at risk. Attacks carried out by nation states and associated non-state actors are growing increasingly frequent and more damaging. While governments must help cultivate trust in cyberspace, it is equally important that technology providers take action to create a trustworthy environment for internet users. There has never been a greater need for the technology industry – the creators, operators, protectors, and first responders for cyberspace – to agree and champion a common set of principles and behaviours to protect civilians in cyberspace.

Since its inception, the security paradigm underpinning the protection of digital technology has been the domain of specialists. Research also shows that it is a security paradigm that non-specialists often find abstract, obscure and difficult to relate to. In this talk I argue that engaging with the protection of digital technology from the viewpoint of the security of people and society creates a more inclusive approach to digital security and a digital security paradigm for everyone. Using a case study, I set out digital security design principles that can be used to develop inclusive approaches digital security.

*** CANCELLED *** The seminar will be rescheduled for a later date.  Modern brain implants provide fantastic new opportunities for treating neurological disorders, but they may also be vulnerable to cyber attacks. In this talk, I will give an overview of the security risks posed by neurological implants, the ethical implications of attackers gaining access to our brains, and what can be done to reduce our chances of ending up in a sci-fi dystopia. See for background: https://www.independent.co.uk/life-style/gadgets-and-tech/news/brain-implants-hackers-memory-neurostimulators-cyber-security-privacy-manipulate-memories-kaspersky-a8611361.html

Digital consumer security is different to enterprise security in terms of priorities and constraints. In this talk I will offer the consumer perspectives on cyber security from the perspective of a large financial services organisation. I will outline the balance between usability and security and how sometimes these aspects are in conflict. In addition I will outline some practical methods used to test customer behaviours and appetites and offer a view on future trends.

Abstract:Many cities and their citizens are witnessing an unprecedented transformation attributed to the high penetration rate of digital technologies and services. The industry leaders racing for the establishment of the 5G standards and the high prioritisation of a sustainable growth agenda seem to be driving the evolution of the smart city paradigm. At the same time, Circular Economy is gaining the attention of major stakeholders (such as the European Commission) and policy makers. Circular Economy is defined as an economy that is restorative and regenerative by design, and which aims to keep products, components and materials at their highest utility and value at all times. In the modern, ICT-driven world, Circular Economy is expected to leverage the data generated and consumed by the assets in order to achieve a high utilisation. The term Data-Driven Circular Economy refers to the development of intelligent assets through the use of digital technologies such as IoT, networking as well as big data and AI to allow real-time decision making and optimisation in order to solve sustainability challenges. Inevitably, such systems are expected to expose a substantially large attack surface. In this talk we will explore through a number of use cases some representative security challenges in data-driven Circular Economy ecosystems in the context of smart cities.

AI and robot ethics have recently gained a lot of attention because adaptive machines are increasingly involved in ethically sensitive scenarios and cause incidents of public outcry. Much of the debate has been focused on achieving highest moral standards in handling ethical dilemmas on which not even humans can agree, which indicates that the wrong questions are being asked. While traditionally engineered artefacts, including AI, require the designer to ensure ethical compliance, learning machines that change through interaction with people after their deployment cannot be vetted in just the same way. I will argue that in order to progress on this issue, we need to look at it strictly through the lens of what behaviour seems socially acceptable, rather than idealistically ethical. Machines would then need to determine what behaviour is compliant with social and moral norms, and therefore be receptive to social feedback from people. I will discuss a roadmap of computational and experimental questions to address the development of socially acceptable machines, and emphasize the need for social reward mechanisms and learning architectures that integrate these while reaching beyond limitations of traditional reinforcement-learning agents. I suggest to use the metaphor of “needs” to bridge rewards and higher level abstractions such as goals for both communication and action generation in a social context. We then suggest a series of experimental questions and possible platforms and paradigms to guide future research in the area.

Thanks to Machine Learning (ML) techniques, computers learn to recognize profiles and trends, make decisions or react autonomously to dynamic environments. Although ML's algorithms are known, the datasets used to train them are usually not public and, in fact, can be protected by privacy laws, or can be kept as trade secrets. This presentation focuses on ML classifiers and how sensitive information associated with the training dataset can be reconstructed through legitimate interactions with them. The Generative Adversarial Networks (GANs) model is presented and it illustrates how GAN neural networks can be used to attack other automatic learning systems.  In particular, it is shown that it is possible to deduce sensitive information from ML classifiers. This information leakage can be exploited, for example, by a competitor to build more effective classifiers, to acquire sensitive user data, or to acquire trade secrets by interacting with an apparatus, potentially violating its intellectual property rights.