Project Description: Machine Learning (ML) systems are vital components of everyday products and services in our society. ML models have been popularly employed in law enforcement (e.g., COMPASS), legal use cases (e.g., LegalBERT), and programming language tasks (e.g., CodeBERT, Github Copilot, etc.). Despite the criticality of these use cases, ML systems are often biased towards … full description “Analyzing the Evolution of Fairness properties in ML-based Code repositories (available)”
Category: Security Behaviours
Attacking Large Pre-trained Programming Language Models (PLMs) via Backdoors (completed)
Project Description: Backdoors refer to a class of Machine Learning (ML) attacks where an adversary trains an ML model to intentionally misclassify any input to a specific label [1]. This is typically achieved by poisoning the training data, such that inputs are misclassified to a target label when the backdoor trigger is present. For instance, … full description “Attacking Large Pre-trained Programming Language Models (PLMs) via Backdoors (completed)”
Cybercrime and ransomware groups – data analysis (available)
Project background Cybersecurity is the practice of defending computers, servers, mobile devices, electronic systems, networks, and data from malicious attacks, in an ever increasingly complex threat landscape. These attacks constitute a variety of computer-enabled and computer-dependent crimes, broadly categorised as ‘cybercrime’. In order to be in a position to defend against these attacks and minimise … full description “Cybercrime and ransomware groups – data analysis (available)”
National cultures and security behaviours (available)
National culture, namely, the culture in a given country, can be broken down into specific variables. These variables define and influence social norms and behaviours of a society and its individuals. However, they also influence cyber security related perceptions and behaviours. Ans indicative and well-known approach on national cultures is the one by Hofstede, where … full description “National cultures and security behaviours (available)”
OSN Mining Platform – Building a public dataset for fake news research (available)
Project Description According to the Statista, in 2018 the UK had 44 million (66% of the population) active Online Social Networks (OSN) users. Whereas, globally, active OSN user population is 3,397 million. The most popular reason for using the OSN is to stay in touch with friends and family (42% of respondents) and stay up … full description “OSN Mining Platform – Building a public dataset for fake news research (available)”
WebAssembly-based microarchitectural covert channel attacks: capabilities, proof-of-concept, and implications (completed)
WebAssembly-based microarchitectural covert channel attacks: capabilities, proof-of-concept, and implications Microarchitectural covert channels are a threat to data confidentiality in multi-tenant environments (cloud platform, mobile phone, etc.). This type of leakage channel aims at tunnelling information across isolation boundaries (sandboxing, censorship, etc.) by exploiting timing variations during program execution. Indeed, the state of microarchitectural components … full description “WebAssembly-based microarchitectural covert channel attacks: capabilities, proof-of-concept, and implications (completed)”