About

Currently a Ph.D. candidate, supervised by Dr. Fabio Pierazzi, at King's College London, investigating the applications of deep reinforcement learning to cybersecurity.
A passion for the cross-section between artificial intelligence and cybersecurity resulted in collaborations with the Systems Security Research Lab (S2Lab) at UCL and the AI for Cyber Defence Research Centre (AICD) at The Alan Turing Institute. Graduated from King’s College London with a first-class B.Sc. (Hons) in Computer Science specialising in Artificial Intelligence. During undergraduate studies, was awarded the Layton Research Award, the Alan Fairbourn Memorial Prize, and the Associateship of King’s College.
Education
- PhD CandidateKing's College London, United Kingdom, 2023 - Present
- BSc (Hons) Computer Science (Artificial Intelligence)King's College London, United Kingdom, 2020 - 2023
Experience
- Visiting CollaboratorArtificial Intelligence for Cyber Defence (AICD) Research Centre, The Alan Turing Institute, 2023 - Present
- Visiting ResearcherSystems Security Lab (S2Lab), University College London, 2024 - Present
- King's Undergraduate Research FellowKing's College London, 2022 - 2022
Artificial Intelligence
- Deep reinforcement learning applications for Cybersecurity.
- Supervised learning for malware classification.
Cybersecurity
- Malware classification
- Vulnerability discovery.
- Adversarial machine learning.
- Autonomous cyber defence.
Selected publications
Every paper has its own page, explained in the paper's own words with diagrams and the results it reports. See all publications.
-
REPLICANT: Learning Policies for Evading and Hardening Malware Detectors
arXiv preprint (cs.LG)
@misc{mcfadden2026replicant, title={REPLICANT: Learning Policies for Evading and Hardening Malware Detectors}, author={Shae McFadden and Ilias Tsingenopoulos and Mario D'Onghia and Alexander Herzog and Myles Foley and Chris Hicks and Lorenzo Cavallaro and Fabio Pierazzi}, year={2026}, eprint={2608.28499}, archivePrefix={arXiv}, primaryClass={cs.LG} } -
SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
35th USENIX Security Symposium (USENIX Security 26)
@inproceedings{McFadden2026Pitfalls, title={SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity}, author={Shae McFadden and Myles Foley and Elizabeth Bates and Ilias Tsingenopoulos and Sanyam Vyas and Vasilios Mavroudis and Chris Hicks and Fabio Pierazzi}, booktitle={35th USENIX Security Symposium (USENIX Security 26)}, year={2026} } -
Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points
Transactions on Machine Learning Research
@article{ristea2026direction, title={Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points}, author={Dan Ristea and Shae McFadden and Ezzeldin Shereen and Madeleine Dwyer and Sanyam Vyas and Chris Hicks and Vasilios Mavroudis}, journal={Transactions on Machine Learning Research}, year={2026} } -
Building Better Environments for Autonomous Cyber Defence
Workshop on AI for Critical National Infrastructure (AI4CNI) at AAMAS
@misc{hicks2026building, title={Building Better Environments for Autonomous Cyber Defence}, author={Chris Hicks and Elizabeth Bates and Shae McFadden and Isaac Symes Thompson and Myles Foley and Ed Chapman and Nickolas Espinosa Dice and Ankita Samaddar and Joshua Sylvester and Himanshu Neema and Nicholas Butts and Nate Foster and Ahmad Ridley and Zoe M and Paul Jones}, booktitle={Workshop on AI for Critical National Infrastructure (AI4CNI) at AAMAS}, year={2026} } -
DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift
Proc. of the AAAI Conference on Artificial Intelligence
@inproceedings{McFadden2026DRMD, title={DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift}, author={Shae McFadden and Myles Foley and Mario D'Onghia and Chris Hicks and Vasilios Mavroudis and Nicola Paoletti and Fabio Pierazzi}, booktitle={Proc. of the {AAAI} Conference on Artificial Intelligence}, year={2026} } -
One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image
Transactions on Machine Learning Research
@article{shereen2026OnePic, title={One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image}, author={Ezzeldin Shereen and Dan Ristea and Shae McFadden and Burak Hasircioglu and Vasilios Mavroudis and Chris Hicks}, journal={Transactions on Machine Learning Research}, year={2026} } -
The Impact of Active Learning on Availability Data Poisoning for Android Malware Classifiers
Proc. of the Annual Computer Security Applications Conference Workshops (ACSAC Workshops)
@inproceedings{mcfadden2024recovery, title={The Impact of Active Learning on Availability Data Poisoning for Android Malware Classifiers}, author={McFadden, Shae and Kan, Zeliang and Cavallaro, Lorenzo and Pierazzi, Fabio}, booktitle={Proc. of the Annual Computer Security Applications Conference Workshops ({ACSAC Workshops})}, year={2024} } -
Wendigo: Deep Reinforcement Learning for Denial-of-Service Query Discovery in GraphQL
Proc. of the IEEE Workshop on Deep Learning Security and Privacy (DLSP)
@inproceedings{mcfadden2024wendigo, title={Wendigo: Deep Reinforcement Learning for Denial-of-Service Query Discovery in GraphQL}, author={McFadden, Shae and Maugeri, Marcello and Hicks, Chris and Mavroudis, Vasilis and Pierazzi, Fabio}, booktitle={Proc. of the {IEEE} Workshop on Deep Learning Security and Privacy ({DLSP})}, year={2024} } -
TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time (Extended Version)
arXiv preprint (cs.LG)
@misc{kan2024tesseract, title={TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time (Extended Version)}, author={Zeliang Kan and Shae McFadden and Daniel Arp and Feargus Pendlebury and Roberto Jordaney and Johannes Kinder and Fabio Pierazzi and Lorenzo Cavallaro}, year={2024}, eprint={2402.01359}, archivePrefix={arXiv}, primaryClass={cs.LG} } -
Poster: RPAL-Recovering Malware Classifiers from Data Poisoning using Active Learning
Proc. of ACM Conference on Computer and Communications Security (CCS)
@inproceedings{mcfadden2023rpal, title={Poster: RPAL-Recovering Malware Classifiers from Data Poisoning using Active Learning}, author={McFadden, Shae and Kan, Zeliang and Cavallaro, Lorenzo and Pierazzi, Fabio}, booktitle={Proc. of {ACM} Conference on Computer and Communications Security ({CCS})}, year={2023} }
News
-
Co-organizing the 4th Machine Learning and Cyber Security Symposium (ML-CSS)
-
Tesseract has been selected as a finalist in the ACSAC Cybersecurity Artifact Competition.
-
Passive recovery paper accepted at the ARTMAN workshop co-located with ACSAC.
-
GraphQL DoS paper accepted at the DLSP workshop co-located with IEEE S&P.