opportunities

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

Vacancies: Ph.D. Opportunities

This section provides up-to-date information about Ph.D. opportunities under my supervision. Note that the list may not be exhaustive and may include expired opportunities, as it is maintained manually.

Please note: all Ph.D. positions listed on this page are competitive, and a position or its funding is not guaranteed.

Open and Upcoming PhD Opportunities

The Ph.D. in Computer Science position below is open with a rolling deadline, and the CDT is expected to reopen soon. Interested candidates should also consult the official UCL webpages and my LinkedIn profile for the latest information, as new opportunities can become available anytime.

Open

Ph.D. in Computer Science: “Trustworthy AI and Cybersecurity in the Agentic World”

Rolling Deadline: March 30, 2027 Home Candidates 4-Year, Fully-Funded Full-time Only

A 4-year, fully-funded Ph.D. position at UCL Computer Science on AI and systems security, in line with the topics described under Research Vision. The position is for Home candidates, as funding for overseas candidates is very unlikely. If you are an overseas candidate and believe you have a particularly strong profile, you may still get in touch, but please explain why you think your profile is exceptional for this position.

Project description

The rapid evolution of AI and ML is fundamentally transforming the landscape of systems security. Recent advances, such as large language models (LLMs) and agentic AI systems, are enhancing our ability to automate the detection, investigation, and mitigation of cyber threats, and offer new ways to support analysts in exploring and structuring vast bodies of security knowledge. At the same time, their increasing use brings new security and privacy challenges, including novel attack vectors against AI-enabled applications, models that may behave unpredictably in complex environments, and evolving adversarial tactics that target both traditional systems and AI-driven defences. This calls for AI in security that is not just powerful, but also trustworthy, transparent, and truly supportive of human users.

Current research has exposed limitations in both AI models and human workflows. Models can fail under evolving threats (concept drift), be compromised by misleading or incomplete data, or miss subtle real-world attacker behaviors due to oversimplified problem settings. In parallel, human analysts often face cognitive overload and lack effective tools to investigate, interpret, and respond to sophisticated attacks.

This Ph.D. will develop AI/ML techniques for systems security that are robust, explainable, and directly beneficial to real-world practitioners. The direction can be tailored to the candidate's strengths and interests. Suggested research directions include (but are not limited to):

  • Designing frontier AI-driven systems for complex, realistic security tasks that go beyond simple detection (e.g., multi-step intrusion analysis, cross-domain threat hunting), focusing on workflows and decision support that analysts actually need;
  • Evaluating the security and deployment trade-offs of Small Language Models (SLMs) for systems security tasks, including their vulnerabilities, performance, and cost benefits in real-world settings;
  • Investigating how agentic AI systems introduce new attack surfaces in core systems security scenarios, such as automated intrusion response, threat investigation, or privilege escalation;
  • Conducting co-design user studies and empirical evaluations with security analysts to ensure that proposed methods genuinely help practitioners in their day-to-day work;
  • Developing transparent, interpretable models or tools that foster trust and collaboration between AI systems and human experts;
  • Establishing principled evaluation frameworks and robust datasets that reflect realistic, evolving environments, so that research outcomes have genuine practical impact.

I am also open to candidates proposing their own ideas in this space, inspired by my team's research and your own interests. There is flexibility in the scope of the project.

Ideal candidate: a BSc/MSc in Computer Science or a related field, a solid background in AI and/or systems security, and a strong interest in trustworthy AI for security. Programming experience (ideally Python) is expected. A strong foundation in either cybersecurity or machine learning is important, but limited experience in one of them is not a deal breaker: curiosity and a willingness to bridge gaps are valued just as highly.

Reopening soon

CDT in Cyber-Physical Risk (next intake)

Home Candidates Only 4-Year, Fully-Funded Full-time Only

The EPSRC Centre for Doctoral Training in Cyber-Physical Risk is expected to reopen soon for its next intake of 4-year, fully-funded Ph.D. studentships, for Home candidates only. Details and deadlines will be posted here once available.

Projects:

“Risk assessment and mitigation of threats to AI-enabled devices in cyber-physical-social systems”

Project description

Artificial Intelligence (AI) and Machine Learning (ML) have been widely adopted both for automated decision making (e.g., smart home automation) and for threat detection. However, this creates new opportunities for malicious actors to conduct “adversarial attacks” to compromise the security and privacy of AI-enabled device users. While the security and robustness of AI has been studied in many digital systems security scenarios (e.g., malware detection, network intrusion detection), it has been less explored in hybrid cyber and physical systems, where attacks may have different risk and impact. For example, systems including home automations, and industrial IoT devices that interact with humans. This project will design new risk assessment methodologies of AI-enabled devices in Cyber-Physical-Social Systems (CPSS), which is crucial to understand how AI security intertwines with the physical world, what hybrid mitigations need to be put in place, and how to produce evidence to inform AI policy makers and regulators.

More projects may become available. If you have your own topic of interest at the intersection of cyber and digital, please reach out.

Programme details:

Closed PhD Opportunities

Show closed opportunities (3)

Closed

“Explainable, Knowledge-driven AI and ML for Systems Security”

Deadline: April 10, 2026 Home Candidates Only

Closed

CDT in Cyber-Physical Risk: “Risk assessment and mitigation of threats to AI-enabled devices in cyber-physical-social systems”

Deadline: February 15, 2026 Home Candidates Only

Closed

“Rethinking Intrusion Detection with Advanced AI for Explainable, Robust and Cost-Aware Decisions”

Deadline: January 5, 2026 (13:00 UK time) Home/International Candidates

This list was last updated on October 21st, 2026.

Vacancies: PostDoc Opportunities

I currently have no PostDoc openings.

Research Vision

My research focuses on developing adaptive cybersecurity solutions by leveraging behavioral modeling, knowledge-driven systems, and the latest advances in artificial intelligence. A core theme of my work is ensuring that these models are not only effective at identifying emerging threats and novel attack patterns, but also produce interpretable and explainable decisions that empower security analysts to make informed responses.

I am especially interested in adversarial and dynamically evolving environments, where classic detection methods often break down due to shifting threats and adaptive attackers. My research includes approaches for embedding expert knowledge into AI-driven systems, such as neurosymbolic AI, to improve their trustworthiness, robustness, and transparency. I am also keen to study the opportunities and risks posed by emerging technologies like large language models (LLMs) and agentic AI systems, while keeping a practical focus on cost-effective solutions, for example by exploring the use of small language models (SLMs).

If you’d like to get a sense of my research interests and whether this area excites you, I encourage you to browse some of my latest papers.

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

  • Embedding Expert Knowledge in ML Systems for Security
  • Explainable Security solutions
  • Trustworthy Dataset Curation
  • AI-Driven Threat Detection, including novel applications of Small Language Models (SLMs)
  • Automated Security Testing
  • Co-designing AI-driven solutions to support analysts in real-world security investigations, ensuring methods are genuinely practical and user-centric

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 Python. 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.

If you are interested in doing a Ph.D. in Computer Science under my supervision at UCL, 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). In your e-mail, please clearly state your fee eligibility status (Home or Overseas), as most funded positions are restricted to Home candidates.

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

Please note that you will always be evaluated by one or more committees, and your admission does not arbitrarily depend on me.

If you insert “Tonberry 3.0” in your e-mail subject, it will increase your chances of receiving a response from me, since I will know you have read this page. I receive many applications, and some of them are very de-contextualized.

Research Visitors

I am generally happy to host Ph.D. students and PostDocs as visitors (who can visit with their own funding), but I have been slowing down the intake because of my workload. If you have a specific project that you would like to do, please make sure to mention that in your e-mail, as it may affect which visitors to prioritize.

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