Post doctor
1 month ago
Project description
and working tasksThe rapid development of autonomous systems, connected devices, and distributed applications poses several challenges in dealing with petabytes of data in diverse resource-constrained environments. Federated machine learning (FML) is a collaborative learning solution to handle these problems without sharing data with centralised servers. However, several emerging threats target FML training, learning, and inference to fail or mislead models at early learning rounds, particularly backdoor and bitflip attack and defence strategies under-explored in FML. These results jeopardize achieving trustworthy performance for any downstream tasks. Therefore, this project envisions developing and validating attack and defence strategies in federated learning for limited and diverse non-iid (independent identically distributed) data under non-standard and adversarial settings, which are ideally suited for edge AI infrastructures. These goals can be achieved by inducing unique features in federated learning algorithms such as robust training, model restoration, trustworthy device selection, secure learning and inference, fault-tolerance against failures and attacks, as well as resilient, fair and robust models. The ambition is to validate them in classical non-standard settings and apply them to solutions for constraint environments (e.g., the Internet of Things (IoT) and robotic arms). Potentially, teaching up to a maximum of 20% can be included in the work tasks.
Qualifications
To be appointed under the postdoctoral agreement, the postdoctoral fellow is required to have completed a doctoral degree or a foreign degree deemed equivalent to a doctoral degree. This qualification requirements must be fulfilled no later than at the time of the appointment decision.
To be appointed under the postdoctoral agreement, priority should be given to candidates who completed their doctoral degree, according to what is stipulated in the paragraph above, no later than three years prior. If there are special reasons, candidates who completed their doctoral degree prior to that may also be eligible. Special reasons include absence due to illness, parental leave, appointments of trust in trade union organisations, military service, or similar circumstances, as well as clinical practice or other forms of appointment/assignment relevant to the subject area. Postdoctoral fellows who are to teach or supervise must have taken relevant courses in teaching and learning in higher education.
Candidates are expected to have solid foundations in the theory and algorithms of project-related areas, such as federated machine learning, backdoor attacks and defence strategies for federated learning, distributed systems, and excellent programming ability.
A strong command of both written and spoken English language is a key requirement.
Besides creativity and a curious mind, important personal qualities include the ability to work independently as well as together with others either in a group or outside. You are also expected to have a willingness to develop yourself continuously to become a competent and independent researcher.
Knowledge and experience in federated learning algorithms, distributed algorithms, data-centric optimization, resilient or fault-tolerant distributed learning, security for federated learning, mathematical statistics, edge AI, etc., is desirable.
-
Post doctor
1 week ago
Umeå, Sweden Umeå University Full timeProject description and working tasks Interactions between malaria parasites and mosquitoes determine the success of malaria transmission and are coming in focus as targets for interventions. The biology of Plasmodium mosquito stages remains poorly understood, but recent breakthroughs in CRISPR screening technologies, single cell transcriptomics, imaging...
-
Umeå, Sweden Umeå University Full timeProject description Single bacterial genomics and transcriptomics holds a great promise of improving our understanding of the microbiology world, discovering new enzymatic activities, or identifying the antibiotic resistance amongst others. Bacterial populations exhibit significant heterogeneity, allowing distinct cell subgroups to thrive in diverse...
-
Umeå, Sweden Umeå University Full timeProject description and tasks In the 80’s and 90’s a surprising phenomenon was observed by physicists: It seemed like certain complicated geometric objects (Calabi-Yau manifolds) appeared in pairs, one taking the form of a mirror image of the other. The phenomenon was dubbed mirror symmetry and similarly as for other duality principles in mathematics,...
-
Umeå, Sweden Umeå University Full timeProject description and tasks In the 80’s and 90’s a surprising phenomenon was observed by physicists: It seemed like certain complicated geometric objects (Calabi-Yau manifolds) appeared in pairs, one taking the form of a mirror image of the other. The phenomenon was dubbed mirror symmetry and similarly as for other duality principles in mathematics,...
-
Umeå, Sweden Umeå University Full timeProject description and tasks Machine learning (‘artificial intelligence’) is having an immense impact on both society at large and research especially, and this impact is expected to increase. This boom is driven by so-called deep neural networks, a class of machine learning models proven incredibly powerful, versatile, and capable of solving many...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject description and tasks Machine learning ('artificial intelligence') is having an immense impact on both society at large and research especially, and this impact is expected to increase. This boom is driven by so-called deep neural networks, a class of machine learning models proven incredibly powerful, versatile, and capable of solving many machine...
-
Umeå, Sweden Umeå University Full timeProject description and tasks Machine learning (‘artificial intelligence’) is having an immense impact on both society at large and research especially, and this impact is expected to increase. This boom is driven by so-called deep neural networks, a class of machine learning models proven incredibly powerful, versatile, and capable of solving many...
-
Umeå, Sweden Umeå University Full timeProject description and tasks This project addresses a fundamental topic in evolution concerning how and why microbes interact in the ways they do. We know that microbes have many possible options, or strategies, regarding what resources they consume to grow. Depending on these choices, pairs of microbes may either compete or cooperate. What actually...
-
Umeå, Sweden Umeå University Full timeProject description and tasks This project addresses a fundamental topic in evolution concerning how and why microbes interact in the ways they do. We know that microbes have many possible options, or strategies, regarding what resources they consume to grow. Depending on these choices, pairs of microbes may either compete or cooperate. What actually...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject description and tasks This project addresses a fundamental topic in evolution concerning how and why microbes interact in the ways they do. We know that microbes have many possible options, or strategies, regarding what resources they consume to grow. Depending on these choices, pairs of microbes may either compete or cooperate. What actually...
-
Umeå, Sweden Umeå University Full timeProject description and tasks Deep learning has enjoyed tremendous success on an impressive number of complex problems. However, the fundamental mathematical understanding of deep learning models is still incomplete, presenting exciting research problems spanning areas such as differential geometry, numerical analysis, and dynamical systems. Neural...
-
Umeå, Sweden Umeå University Full timeProject description and tasks Deep learning has enjoyed tremendous success on an impressive number of complex problems. However, the fundamental mathematical understanding of deep learning models is still incomplete, presenting exciting research problems spanning areas such as differential geometry, numerical analysis, and dynamical systems. Neural...
-
Umeå, Västerbotten, Sweden Sveriges Lantbruksuniversitet Full timeDepartment of Forest Resource ManagementThe Department of Forest Resource Management conducts teaching and research in the areas of Forest Remote Sensing, Mathematical Statistics Applied to Forest Sciences, Forest Inventory and Sampling, Forest Planning and Landscape Studies. The Department is also responsible for several environmental monitoring and...
-
Umeå, Västerbotten, Sweden SLU´s web Full timeProject Officer position at the Division of Forest Remote Sensing Reference number Department of Forest Resource ManagementThe Department of Forest Resource Management conducts teaching and research in the areas of Forest Remote Sensing, Mathematical Statistics Applied to Forest Sciences, Forest Inventory and Sampling, Forest Planning and Landscape Studies....
