SEMINÁRIO | “Artificial Intelligence and Cybersecurity: The (lack of) security of Machine Learning models” by João Vitorino

There are several technological and ethical challenges that undermine the trustworthiness of Machine Learning. One of the main challenges is the lack of robustness, which is an essential property to ensure that ML models are used in a secure way. Improving robustness is no easy task because the models are inherently susceptible to adversarial examples: data samples with subtle perturbations that cause unexpected behaviors. ML engineers and security practitioners still lack the knowledge and tools to prevent such disruptions, so adversarial examples pose a major threat to ML and to the intelligent systems that rely on it.

“Artificial Intelligence and Cybersecurity: The (lack of) security of Machine Learning models” will be presented by João Vitorino (ProDEI student), March 21, at 14:00, room I -115.

Short Bio:

João Vitorino is a researcher at GECAD, an R&D unit of ISEP, and a PhD candidate at FEUP, in the Doctoral Program in Informatics Engineering. He holds a Master’s degree in Artificial Intelligence Engineering, in addition to several certifications in the fields of AI and computer networking. He has collaborated with various companies and institutions in international R&D projects, and has been responsible for the conceptualization and development of AI solutions for several real-world cybersecurity applications.
The focus of his work has been adversarial robustness in complex tabular data domains. He has developed an intelligent method that performs realistic adversarial attacks, and training mechanisms that provide secure ML models for complex tasks like cyber-attack classification. João was awarded the “2023 Outstanding MSc Thesis Award”, by IEEE Portugal Section. His thesis “Realistic Adversarial Machine Learning to improve Network Intrusion Detection” analyses the robustness of machine learning algorithms and proposes the “AP2M – Adaptive Perturbation Pattern Method”.

DEI TALKS | “A Survey of Tasks Derived from or Related to Natural Language Inference” by Prof. Martin Víta

“Natural language inference (recognizing textual entailment task in the past) belongs to the most prominent tasks in current NLP, it is a keystone of natural language understanding. NLI can be stated as a classification task whether a given hypothesis can be inferred from a  given premise. In this talk, we are going introduce a large variety of tasks accompanied by illustrative examples and review corresponding state-of-the-art results. This talk may serve as starting point for anyone who want to apply new approaches and models to investigate these not so much known tasks (as well as apply them in downstream applications).”

A Survey of Tasks Derived from or Related to Natural Language Inference” will be presented February 23, at 17:00, room I 025, moderated by Prof. Carlos Soares (DEI).

Martin Víta graduated at the Faculty of Mathematics and Physics, Charles University in Prague in the field of discrete models and algorithms. Later, he obtained PhD degree at the Faculty of Informatics, Masaryk University in Brno in natural language processing. Currently, he serves as an assistant professor at the Faculty of Informatics and Statistics, Prague University of Economics and Business where he teaches mathematics and text analytics. He is also a researcher at Czech Academy of Sciences where he focuses in ML and text mining topics.”

Creativity Talks | “Shaping Technology with Moral Imagination: The Creative Act of Value Sensitive Design” by Batya Friedman

The thirteenth session of the Creativity Talks, the first of 2024, will have as keynote speaker the distinguished University of Washington Professor Batya Friedman, a value sensitive design (VSD) pioneer, an approach that takes human values into account when designing technical systems. She will demonstrate how her work in this area has resulted in robust theoretical constructs, dozens of innovative methods and practical toolkits such as Envisioning Cards. Value-sensitive design has been widely adopted and is currently used in architecture, biomedical informatics, civil engineering, cybersecurity, energy, global health, human-computer interaction, human-robotics interaction, information management, legal theory, moral philosophy, technology policy, transport and urban planning, among other areas.

“Shaping Technology with Moral Imagination: The Creative Act of Value Sensitive Design” will be presented February 22, 18:00, on the You Tube channel of the C Talks, The session will be moderated by Prof. Eliana Santiago, Assistant Professor of the Faculty of Fine Arts of the University of Porto.

All the information on this talk can be seen on the Creativity Talks webpage.

Batya Friedman is a Professor in the Information School and holds adjunct appointments in the Paul G. Allen School of Computer Science & Engineering, the School of Law, and the Department of Human Centered Design and Engineering at the University of Washington where she co-founded the Value Sensitive Design Lab and the UW Tech Policy Lab. At the heart of Dr. Friedman’s work lies a fascination with cultivating moral and technical imagination. Dr. Friedman pioneered value sensitive design (VSD), an approach to account for human values in the design of technical systems. Over the course of three decades, her work in value sensitive design has resulted in robust theoretical constructs, dozens of innovative methods, and practical toolkits such as the Envisioning Cards. Value sensitive design has had wide appeal globally where it has been used in architecture, biomedical health informatics, civil engineering, computer security, energy, global health, human-computer interaction, human-robotic interaction, information management, legal theory, moral philosophy, tech policy, transportation, and urban planning, among other fields. Additionally, value sensitive design is emerging in higher education, government, and industry as a key approach to address computing ethics and responsible innovation. Today, Dr. Friedman is working on open questions in value sensitive design including multi-lifespan design, and designing for and with non-human stakeholders – questions critical for the wellbeing of human societies and the planet.”

Presentation of DEI’s Master Programmes

The Department of Informatics Engineering will promote a session aimed to introduce the master programmes hosted by this department. The session will be held on Wednesday afternoon, February 14, in FEUP Auditorium.
It will be an opportunity for undergraduate students to find out details about these masters, their areas of study, employability and the prospects associated with attending a second cycle of studies.
This session aims to provide guidance and clarification, thus making the choice a little easier when it comes to submitting an application.

Programme
14:45 | Reception of participants
15:00 | Opening Session
15:15 | Presentation M.EIC – Master in Informatics and Computing Engineering (Prof. Rui Rodrigues)
15:30 | Presentation M.IA – Master in Artificial Intelligence (Prof. João Cardoso/ Prof. João Pedro Pedroso)
15:45 | Presentation MM – Master in Multimedia (Prof. Jorge Barbosa)
16:00 | Presentation MCI – Master in Information Science (Prof. Carla Teixeira Lopes)
16:15 | Presentation MESW – Master in Software Engineering (Prof. João Pascoal Faria)
16:30 | Presentation MECD – Master in Data Science and Engineering (Prof. José Luís Borges)
16:45 | Q&A (with intervention from the secretariat)

The session is free and does not require registration. Everyone is invited!

DEI TALKS | “Architectures for building Extraordinary Software” with Joseph Yoder, Graziela Simone Tonin, Neil Harrison and Filipe Correia

When building complex systems, it can be all too easy to primarily focus on features and overlook software qualities, specifically those related to the architecture. Pressure to adapt to and shape the market requires organizations to add new features, accommodate new interactions, and have new teams work on adapting the software. Some believe that by simply following Agile practices—starting as fast as possible, keeping code clean, and having lots of tests—a good architecture will magically emerge. While an architecture will emerge, if there is not enough attention paid to the architecture and the code, technical debt, and design problems will creep in until it becomes muddy, making it hard to deliver new features quickly and reliably. Sometimes a straightforward software architecture that starts out small when communication is easy can support guided, incremental architectural changes and can gradually evolve with its environment, remaining fit for its purposes. Other times it is not so simple: the initial software architecture can be poorly suited for supporting required changes, or the accumulation of suboptimal architectural decisions (also known as architectural technical debt) can be too severe. It is essential to have a sustainable architecture that can evolve through the project life-cycle. Sustainable architecture requires ongoing attention, especially when there are evolving priorities, a lot of technical risks, and many dependencies. This will be a roundtable spirited discussion by invited panelists and participants discussing architectural considerations for designing systems, specifically on architectures for building excellent software.

“Architectures for building Extraordinary Software” will be presented February 7, 15:00-16:15, in room B033 and will be moderated by Carlos Duarte (DEI).

 

Short Bios:

 Joseph (Joe) Yoder is a research collaborator at IME/USP, president and a fellow of the Hillside Group (www.hillside.net), a group dedicated to improving the quality of software development, and is a founder and principal of the Refactory (www.refactory.com), a company focused on software architecture, design, implementation, consulting, and mentoring on all facets of software development. He is best known as an author of the “Big Ball of Mud” pattern, illuminating fallacies in software architecture. Joe is also a co-author of “A Scrum Book: The Spirit of the Game”; which includes 94 patterns and 2 pattern languages about getting the most out of Scrum. Joe teaches and mentors developers on agile and lean practices, architecture, flexible systems, clean design, patterns, refactoring, and testing. Joe has presented many tutorials and talks, arranged workshops, given keynotes, and helped organize leading international agile and technical conferences. Joe believes software is still too hard to change and wants to do something about this. Recently, the ACM recognized Joe as a Distinguished Member in the category of “Outstanding Engineering Contributions to Computing” and the Hillside Group awarded Joe as a Hillside Fellow.”

Graziela Simone Tonin has worked in the technology market for over 19 years in Brazil and abroad. Ph.D. in Computer Science. She received the US IBM World Award and the Women of Value Award. Graziela mentors and worked in several national entrepreneurship and innovation programs, such as Innovativa Brasil. Ambassador of Clube Bora Fazer, an entrepreneurship community. She works as a professor at Insper Institution, a Teacher of Executive Education and customized programs for C-Levels, and also is a professor in the Computer Science and Engineering program. She led the Women In Tech Project and co-leader in the Gender Front of the Diversity Committee at Insper. Graziela leads volunteer projects throughout Brazil through the Grupo Mulheres do Brasil. In addition, she is part of a worldwide research project that analyzes initiatives aimed at women in software engineering.”

Neil Harrison is a professor and former head of the Department of Computer Science at Utah Valley University, USA. He led the department for seven years, in which he directed the creation of three new baccalaureate programs and two new emphases within the BS in Computer Science program. He oversaw the rollout of a graduate program. He led the accreditation of the software engineering program, and the re-accreditation of the computer science program.

Dr. Harrison is the author of over twenty-five widely cited articles in the areas of software patterns, software architecture, and software engineering and organizations. He is the co-author of the book, “Organizational Patterns of Agile Software Development.” He has been a leader in the software patterns movement and is the namesake of the “Neil Harrison Shepherding Award”, which is awarded annually at patterns conferences. He has been an invited speaker and keynote speaker at conferences, including Agile Portugal. Dr. Harrison holds a PhD from the University of Groningen (the Netherlands), an MS from Purdue University and a BS from Brigham Young University, all in computer science.”

Filipe Correia is a professor of Software Engineering at the University of Porto / FEUP and a researcher at INESC TEC. In the past, he played other roles, from software architect to coach, to developer.His research interests tend to revolve around software design, architecture, agility, and DevOps. In the last few years, his work has been focusing on microservice-based architectures and the highly maintainable and flexible systems they allow to create, and on strategies to improve the Developer Experience across the software development lifecycle. You can find more information on Filipe’s website.”

Carlos Duarte (Moderador) is a software engineer and researcher at INESC TEC. He is also a PhD student at FEUP’s ProDEI, and an invited assistant lecturer at FEUP (software engineering course). He previously worked at DevScope. His research interests revolve around software architecture, more specifically architectural erosion and evolution. Currently, he is researching the relationship between architectural erosion and technical debt, and how software visualization techniques can help identify and prevent erosion from affecting software systems. His Master thesis focused on improving the refactoring experience in IDEs, allowing the creation of custom refactoring tools by describing detection and transformation patterns using a DSL. The thesis won the 2022 Vestas award for best Master thesis in informatics engineering at FEUP.”

DEI TALKS | “Let’s discuss about Models and Languages for embedded systems in Industry 4.0” by Prof. Julio Medina

“This talk proposes to have a conversation about the trends in conceptual modelling languages used for the design and analysis of real-time and embedded systems in the context of the ever changing industrial environments but never changing business demands”.

Let’s discuss about Models and Languages for embedded systems in Industry 4.0” will be presented February 1, at 11:00, room I-105, moderated by Prof. Gil Gonçalves (DEI).

Short Bio:
“Julio Medina is Associate Professor at Universidad de Cantabria, Spain. His main research areas include the modeling of real-time distributed systems for schedulability analysis and dependability, standards and languages for the representation of such models, and their usage for modular and component-based development software engineering strategies. He contributes to the OMG in the standardization of languages like SysML, MARTE, UCM, UTP, among others.”

Talk a Bit is back for its 12th edition

*Talk a Bit is back on stage at the FEUP Auditorium next Saturday, February 3.

The theme of this 12th edition, “Today’s Choices, Tomorrow’s World“, will highlight the profound impact of contemporary technological decisions on the future.

The programme will feature insightful talks and discussions on Artificial Intelligence (AI) and its role in health, smart cities and sustainable industries. Several experts will share with the public their knowledge on the latest technological advances and their future implications, promoting an environment conducive to learning and socializing opportunities.

Hugo Neves (MOG), Filipe Portela (IOTECH), Luís Valente (ILOF) and Tiago Reis (DIGESTAID) have all been confirmed as guest speakers in a programme (being updated) that can be seen here.

Registration is free but mandatory and must be submitted here.

*Talk a Bit is a technology conference organized by the students of the Master’s Degree in Informatics and Computing Engineering at the Faculty of Engineering of the University of Porto.

PhD Defense in Informatics Engineering : ”Highly reconfigurable smart component system”

Candidate
Luís Carlos de Sousa Moreira Neto

Date, Place and Time
January 31, 14:15, Sala de Atos FEUP

President of the Jury
Carlos Miguel Ferraz Baquero-Moreno, PhD, Full Professor, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto.

Vogais
Julio Luis Medina Pasaje, PhD, Associate Professor, Departamento de Ingeniería Informática y Electrónica, Facultad de Ciencias, Universidad de Cantabria, Espanha;
António Eduardo Vitória do Espírito Santo, PhD, Assistant Professor, Department of Mechanical Engineering, Faculdade de Engenharia, Universidade da Beira Interior;
Pedro Nuno Ferreira da Rosa da Cruz Diniz, PhD, Full Professor, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto;
Luis Miguel Pinho de Almeida, Associate Professor with Habilitation, Department of Electrical and Computer Engineering, Faculdade de Engenharia, Universidade do Porto;
Gil Manuel Magalhães de Andrade Gonçalves, PhD, Assistant Professor, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto (Supervisor).

Abstract:
“Across all sectors of our society, efficiency is an increasingly paramount concern for a sustainable world. While the significance of efficiency spans all levels, it is at a large scale where the impacts of efficient practices are most prominently noticed. Industrial activities are an example of how efficiency traduces in visible results. It doesn’t require extensive reasoning to recognize that everyday increasingly affordable goods we consume are a direct outcome of these efficiency demands. The market is demanding new services and business models that center the end user in the product design. In the near future, consumers will be able to customize a product on-line, place a production order, and see it delivered, all in the same day. This remarkable possibility arises from of a combination of efficiency and flexibility within the production processes. Several names have been used to describe the same fundamental paradigm in both academic and industrial contexts: Factories of the Future, Smart Manufacturing and Industry 4.0, all remounting to the same technological advent. This concept has far-reaching implications, extending its influence across multiple technological domains, presenting a wealth of research opportunities and driving the need for innovative technologies. This thesis delves into two technological domains related with this new paradigm and tackles one key problem in either domain. Within the Cyber-Physical Production Systems (CPPS) domain, it addresses the problem of establishing a unified network of industrial assets where software and its connections to other assets are clearly discernible and recognized. On the Reconfigurable Manufacturing Systems (RMS) domain, it addresses the fast pace at which the production lines will have to reconfigure, in particular, how software will have to reconfigure in parallel with the production lines and the ease with which new software can be developed and deployed to meet emerging challenges. A solution to both problems emerges from the field of Component-Based Software Engineering (CBSE), where this thesis drew inspiration to develop an innovative Smart Component with enhanced software reconfiguration and deployment capabilities. The proposed system exploits using Linux, a general-purpose operating system, as the component runtime environment (RTE). A combination of shared memory for efficient component communication and parallel and reconfigurable computing properties for enhanced throughput allows the proposed system to meet established application performance standards while maintaining a high degree of flexibility and reusability. The Smart Component’s flexibility is demonstrated through the implementation of two component models. The IEC 61499 component model, designed to model event-driven distributed applications for industrial system monitoring and control, and the Smart Object Self-Description (SOSD), developed by the author to describe software components, their interconnections, and their associations with industrial assets. The IEC 61499 implementation was directly compared to existing RTEs, outperforming them in real-world use cases and equaling the performance of one RTE in a literature benchmark. Additional benchmarks to assess the Smart Component’s reconfiguration performance and simplified software component development method were proposed in this thesis. The effectiveness of the SOSD implementation was validated through its application in a real-world use case, furnishing other CPPS nodes with context regarding the origin of the collected data and the software components responsible for its processing. By using Linux as the RTE, a software layer traditionally dedicated to manage components was deemed unnecessary, due to the system’s ability to execute applications conforming to relevant performance standards, while showing superior software flexibility, and even outperforming existing RTEs which employ the traditional approach. Many runtime environments for software components exist, but few allow the deployment of components built in more than one programming language, and none – to the best of the author’s knowledge – allow the development of components in any language – provided that language is at least able to read and write to files. The simplicity of developing regular software program for Linux and converting it into a software component is a promising feature that should benefit the development of industrial control and monitoring applications by bringing along the benefits of multiple high-level programming languages.”

DEI TALKS | “Analyzing and Modeling Intelligent Systems Users’ Behavior in Digital Society” by Prof. Humberto Marques-Neto

“Information systems are ever-increasingly intelligent and present in the daily lives of people and companies, facilitating and modifying the performance of various activities. In addition to handling each system’s intrinsic data, data from its users’ interactions can contribute to identifying, modeling, and analyzing people’s behavior patterns. The data analysis from the usage of web systems and mobile applications and, in particular, from online social networks such as Twitter, Facebook, WhatsApp, Instagram, and TikTok (obviously respecting the privacy of users) can contribute to the understanding of some dynamics and specific behaviors of human beings.

In this talk, I will present how our research group has done the characterization, analysis, and modeling of the behavior of users of intelligent information systems, more specifically, users of online social networks and information systems that make information available in open data portals, to induce the development of new software that use machine learning and artificial intelligent algorithms. The information systems user behavior, together with patterns of social interaction and human mobility in urban centers, in addition to subsidizing decisions and policies of government agencies and institutions responsible for urban planning, could foster and even target software developers interested in creating innovative software with the potential to improve people’s lives in a digital and connected society.”

Analyzing and Modeling Intelligent Systems Users’ Behavior in Digital Society” will be presented January 25, at 14:00, room B006, moderated by Prof. Gil Gonçalves (DEI).

Short Bio:
Prof. Humberto T. Marques-Neto is a researcher and a professor in the Department of Computer Science at the Pontifical Catholic University of Minas Gerais (PUC Minas) in Belo Horizonte – Brazil. He holds a degree in Computer Science from the PUC Minas, a Master’s in Information Science, and a Ph.D. in Computer Science, both from the Federal University of Minas Gerais – UFMG. In the last few years, he has published some papers on the characterization and modeling of large-scale distributed system user behavior, online social network analysis and modeling, computing systems for mobile devices, and software engineering. He also coordinates (at PUC Minas) the Center of Technological Innovation and PUCTec, a Hub for Innovation and Business with about 30 startups. Since last August, he has been spending a one-year sabbatical as a Visiting Fellow in the Department of Computer Science of the University of Pisa.”

DEI TALKS| “Aprendizado colaborativo em redes neuronais artificiais” by Prof. Areolino de Almeida Neto

“Any task that cannot be carried out by a single agent requires the interaction of multiple agents aligned with the solution to the problem. Teamwork usually requires coordination between the members so that there are no conflicts and the result is more efficient. In the field of artificial learning, when one element is unable to fully learn the solution to a problem, it requires the participation of other “intelligent” elements to fully learn the solution. In this way, a collaborative learning system is presented, in which intelligent agents learn to collaborate with each other in order to achieve complete learning in a self-coordinated way (without a coordinator) and without the occurrence of conflicts between the intelligent elements. Specifically, it involves inserting other neural networks or other intermediate layers into an ANN in order to collaborate with the learning already acquired and thus add new knowledge to the system.”

This is how Prof. Areolino de Almeida Neto describes his presentation entitled “Collaborative learning in artificial neural networks”, which will take place on 15 November at 14:30, room B033.

The talk will be moderated by Prof Carlos Soares (DEI).

Short Bio

Areolino de Almeida Neto holds a Bachelor’s degree in Electrical Engineering from the Federal University of Maranhão (UFMA) in 1990, a Master’s degree in Aeronautical and Mechanical Engineering from the Technological Institute of Aeronautics (ITA) in 1998 and a PhD in Aeronautical and Mechanical Engineering from ITA / Universität Hannover (2004). He has experience in Electrical Engineering, Mechatronics and Computer Science, with an emphasis on Mechatronic Systems and Artificial Intelligence, working mainly on the following topics: neural networks, reinforcement learning, mobile robotics and manipulator robotics. Since 2015, he has been working as Coordinator of the Aerospace Engineering WG of the Secretariat of Science, Technology and Innovation (SECTI) of Maranhão, Brazil. He has been a permanent member of the Postgraduate Programme in Computer Science at UFMA since 2010, which has allowed him to publish several scientific articles on neural networks and reinforcement learning, and a book on multiple self-coordinating neural networks.