Weekly PhD Newsletter | SIGN UP NOW Weekly PhD Newsletter | SIGN UP NOW

Understanding Distribution Shift with Logic-based Reasoning and Verification

   UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence

  Dr Fabio Pierazzi  Applications accepted all year round  Funded PhD Project (UK Students Only)

About the Project

This project is part of a unique cohort based 4-year fully-funded PhD programme at the UKRI Centre for Doctoral Training in Safe and Trusted AI.

The UKRI Centre for Doctoral Training in Safe and Trusted AI brings together world leading experts from King’s College London and Imperial College London to train a new generation of researchers and is focused on the use of symbolic artificial intelligence for ensuring the safety and trustworthiness of AI systems.

Project Description:

Data-driven approaches have been proven powerful for security detection tasks, eg, for malware detection [a]. However, the arms race between attackers and defenders causes an ever-growing distribution shift in the main characteristics of the detection task, although the expert knowledge modifies slowly. 

This project will define new symbolic AI framework based on logic-based reasoning relying on expert knowledge in the security domain to devise techniques for understanding the root causes of distribution shift [b,c,d]. Understanding how to change reasoning frameworks so to embed expert knowledge and verify whether a certain type of drift is happening (co-variate shift, label shift, or concept shift [b]). This reasoning framework will rely also on knowledge extraction from threat reports. 

The final objective of this symbolic AI framework is to gather a more understanding of the phenomenon and its root causes, as well as understanding logic-based constraints that could be later embedded in data-driven algorithms to improve their resilience against distribution shift. 

How to Apply

The deadline for Round A for entry in October 2023 is Monday 28th November. See here for further round deadlines.

We will also be holding an online information session on Tuesday 15 November 1-2pm: UKRI Centre for Doctoral Training in Safe and Trusted AI - Info Session Tickets, Tue 15 Nov 2022 at 13:00 | Eventbrite

Committed to providing an inclusive environment in which diverse students can thrive, we particularly encourage applications from women, disabled and Black, Asian and Minority Ethnic (BAME) candidates, who are currently under-represented in the sector.

We encourage you to contact Dr Fabio Pierazzi () to discuss your interest before you apply, quoting the project code: STAI-CDT-2023-KCL-17.

When you are ready to apply, please follow the application steps on our website here. Our 'How to Apply' page offers further guidance on the PhD application process.

Funding Notes

Find out more about funding here - View Website


[a] Pendlebury, Feargus, et al. “TESSERACT: Eliminating experimental bias in malware classification across space and time.” _USENIX Security Symposium_, 2019.
[b] Moreno-Torres, Jose G., et al. “A unifying view on dataset shift in classification.” _Pattern recognition_, 2012
[c] Jajodia, Sushil, et al. “A probabilistic logic of cyber deception.” _IEEE Transactions on Information Forensics and Security_, 2017.
[d] Poon, Hoifung, and Pedro Domingos. “Sound and efficient inference with probabilistic and deterministic dependencies.” _AAAI_, 2006.

Email Now

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs