Nettsider med emneord «Security» - Side 2

This project aims at developing models and tools for automated or semi-automated classification and discovery of cyberthreats based on ontologies and semantic reasoning.

This projects involves a cases study and analysis of human users of a security ceremony; i.e., security protocol or procedure where the human is part of the protocol. The current on-line banking is an example, or the recent electronic voting procedure used in Norway. This topic is at the border of security and psychology. Your work will start from a recent paper [28] originating from the group of Ann Blandford.

See project link. Ask for discussions with one of the supervisors, for more information or variations of the project. See also general concerns.

This projects involves a cases study and analysis of human users of a modern information system, like IoT. This topic is at the border of computer science, psychology, cognitive sciences, and AI.

Ask for discussions with one of the supervisors, for more information or variations of the project. See also general concerns.

In this project, we plan to answer this question "do we have some strangely and maliciously constructed images that if they are given to contrastive-based SSL methods and the training is done securely and faithfully, the final features become useless like random features" building on our recent work on robust and secure deep learning [8].  The question is  how much corrupted data is needed. Say if a malicious user uploads 1-2% corrupted data and breaks the learning process (features become like random features), it could be very alarming. But if a lot of corrupt images are needed, then it means that the current systems are quite robust.

The task is to dependently typed programming for certification (especially in the area of security)

Compiler security is an important field. This thesis wants to do groundwork to reproduce a known technique known as{Diverse Double-Compiling (DDC) in an new environment. Potentially with a secondary focus on writing a compiler for a mainstream language.

The task is to design and implement a radmomization concept for Rust compilation