I am always looking for motivated Ph.D. students to join my team at King’s College London. If you are a prospective candidate, I invite you to read this page before contacting me for Ph.D./research opportunities.

My Research Area

My main area of expertise is at the intersection of systems security and machine learning, with emphasis on network security and malware analysis. My research aims to design cybersecurity solutions able to learn behavioral models that can be used to detect novel attacks and threats, and that generate interpretable decisions to assist security analysts in protecting systems and organizations. I am particularly interested in challenging scenarios such as unsupervised learning (e.g., no a-priori attack examples), fast evolving threats (high non-stationarity), and smart adversaries (adversarial ML attacks).

To get a better idea of the type of research I do, and to see if you like it, I recommend you to read/skim some of my latest papers.

I am looking to solve problems in many domains with incoming students, including (but not limited to):

  • Problem-Space Adversarial ML
  • Explainable Security
  • Systems Security
  • Automated security testing
  • Malware Analysis

Prospective Ph.D. Candidates

I am looking for candidates with a BSc/MSc in Computer Science (or analogous), and a strong mathematical and systems security background. Passion and commitment may partially compensate for background deficiencies in either of these two (but hardly for both). You need to be comfortable with scripting and coding, preferably in one or more of Python/Java/C/C++. You must hold a genuine interest with my research agenda, and in improving the state-of-the-art through top-quality publications.

Getting a Ph.D. is extremely challenging and, often times, frustrating. Experiments take long hours and often do not work out as expected. Top conferences have an acceptance rate of 10-15%, which means you will face a lot of rejections. Creating new knowledge is extremely rewarding, but requires creativity, persistence and motivation. This is part of the reason for which I am considering only full-time applications at this point in time.

How to Apply for a Ph.D.

If you are interested in doing a Ph.D. in Computer Science under my supervision at King’s College London, and if you are still keen to after reading the premise above, you should definitely write me an e-mail with your CV and interests (be sure to read all of this page before sending).

Make sure that you really motivate why you were thinking about joining my team, as I receive many applications and I am looking for candidates that stand out in terms of passion and experience.

Please read also the requirements of the KCL Ph.D. Program before writing, if for any reason you may be ineligible. I also offer project(s) within the CDT in Safe & Trusted AI.

Please note that you will be evaluated by a committee, and your admission does not arbitrarily depend on me.

If you insert “Bahamut 3.0” in your e-mail subject line when contacting me, I will know you have read this page, and you will most likely receive a reply from me. Failing to insert this keyword in the subject line may result in your e-mail getting lost in my inbox: I receive a lot of e-mails from prospective graduate students, and sometimes it is hard for me to understand which ones are out of genuine interest in joining my group, or just a “copy-paste” spammed to a lot of professors.

Research Opportunities for KCL BSc Students

I occasionally have research opportunities for self-contained projects for undergraduate students. If you are a student at King’s, you may be interested in looking more into King’s Undergraduate Research Fellowships (KURF).

Research Visitors

I am generally happy to host Ph.D. students and PostDocs as visitors (who can visit with their own funding), and I will prioritize based on capacity and matching interests. King’s College London has an internal program for supporting research visitors.

Please take into account that the process of approval of research visitors which can take about 2-3 months.