#MLandSecurityatImperial



Believing in the power of machine learning in enhancing cybersecurity applications, we host a one-day event that includes a series of talks given by researchers working on the intersection of Machine Learning and Cyber Security at Imperial. Each talk will include the current updates in the speaker field, the associated challenges, and the future directions.



Registration:


Speakers         Attendees



Scroll down for more details...



Details

Location: Lecture Theatre 311, Huxley Building, South Kensington.

Date: Friday, June 14, 2024.

Time: 9:00-17:00

Lightning talks (~15 minutes), keynote preseantations, and networking!


We invite all students, researchers, and professors within Imperial - and invited guests from this audience - to attend!
Coffee/tea and snacks (vegan/gf options available) included for in-person attendees.


For further information, please email f[dot]alotaibi21[at]imperial[dot]ac[dot]uk.


Schedule

This symposium is composed of INFORMAL lightning talks by researchers at Imperial who work in the intersection of machine learning and cyber security. The talks below are about current applied ML&Security research (COMPLETE OR NOT COMPLETE!!) and each talk will be followed by a brief Q&A session with the speaker. These talks are not recorded but online viewing is available to online, registered attendees.

The goal of this event is to connect those who work in this area; we look forward to your active participation!



Time Speaker Talk Title
09:30 Myles Foley - Welcome and House Keeping -
10:00 Myles Foley RL, I Choose You: Using RL to learn mutation strategies in fuzzing
10:20 Shae McFadden Wendigo: Deep Reinforcement Learning for Denial-of-Service Query Discovery in GraphQL
10:40 Javier Carnerero Cano Indiscriminate Data Poisoning Attacks Against Supervised Learning
11:00 Fabio Pierazzi Towards practical deployments of ML for Systems Security
12:00 --- --- LUNCH/NETWORKING ---
13:30 Eman Maali Are we there yet in terms of practicality and ML-based IoT device identification for security?
13:50 Fahad Alotaibi Adaptive One-Class Anomaly Detection for NIDS
14:10 Dr Inam Ullah Khan Robust Big Data Analytics for Intrusion Detection in IoT Network
14:30 Giovanni Cherubin A threat-specific look at Privacy-Preserving Machine Learning
15:30 --- --- BREAK ---
15:50 Abdullah Aldaihan LLM Guided attack investigation using In-Context Learning
16:10 Igor Shilov Copyright Traps for Large Language Models
16:30 Wentao Ma LLM Echo Chamber: personalized and automated disinformation
16:50 --- --- NETWORKING ---
17:10 --- --- Closing remarks ---


If you are a speaker and the assigned time does not work for you, please contact Fahad Alotaibi (fma21[at]ic[dot]ac[dot]uk).


Keynote Speakers

Dr. Fabio Pierazzi

Dr. Fabio Pierazzi

Senior Lecturer in Computer Science at King's College London


Towards practical deployments of ML for Systems Security


Dr. Fabio Pierazzi is a Senior Lecturer (Associate Professor) and Deputy Head of the Cybersecurity group at the Department of Informatics of King's College London. His research interests are at the intersection of systems security and machine learning, with a particular emphasis on settings in which attackers adapt quickly to new defenses (i.e., high non-stationarity, adaptive attackers).



Dr. Giovanni Cherubin

Dr. Giovanni Cherubin

Senior Researcher in Machine Learning & Security at Microsoft Research


A threat-specific look at Privacy-Preserving Machine Learning


Dr. Giovanni Cherubin is a Senior Researcher at Microsoft (Cambridge), working with the Microsoft Security Response Centre (MSRC). Before joining Microsoft, he held research positions at the Alan Turing Institute and EPFL, and he obtained a PhD from Royal Holloway University of London in Machine Learning and Cyber Security. His research focuses on privacy and security properties of machine learning models, and on the theoretical/empirical study of their information leakage. He also works on reliable machine learning tools, such as distribution-free uncertainty estimation for machine learning (e.g., Conformal Prediction).

Sponsors


We gratefully acknowledge the support of this year's sponsors, listed below. Thank you for your contributions!


IBM
DoC@Imperial
Imperial-X
AICD

Organisers

Abdullah Aldaihan

Ph.D. Student in LLM for security at the DoC.

Abdullah is a PhD student in the Security & Machine Learning (SML) Lab at Imperial under the supervision of Dr. Maffeis. He received his MSc in computer science from Georgia Institute of Technology, and his BSc in computer science from King Saud University. Abdullah's focus is on utilizing Large Language Models (LLMs) for systems security.

Fahad Alotaibi

Ph.D. Student in Adaptive Deep Learning for Security at the DoC.

Fahad is a PhD student in the Security & Machine Learning (SML) Lab at Imperial under the supervision of Dr. Maffeis. He received his MSc from The University of York (UK) in Cyber Security, and his BCs from Shaqra University (KSA) in Computer Science. Fahad’ research is focused on robusting deep learning-based security applications againsts concept drift and poisoning attacks. Fahad is also interested in other areas such as digital forensics and ransomware prevention.

Javier Carnerero Cano

Javier Carnerero Cano

Research Scientist at IBM Research and PhD in Machine Learning Security (pending viva) at the DoC

Javier Carnerero Cano is a Research Scientist working on trustworthy AI at IBM Research Europe (Ireland). He is also close to completing his PhD (pending viva) in machine learning security at Imperial under the supervision of Prof Emil C. Lupu and Dr Luis Muñoz González. His current research interests include trustworthy and secure machine learning, bilevel optimisation, generative models, federated learning, and machine unlearning. In his PhD, he focussed on understanding and preventing indiscriminate data poisoning attacks against supervised learning. He also did a research internship at IBM Research in the security of machine unlearning. He obtained his MRes in Multimedia and Communications, and his MSc and BEng in Telecommunications Engineering from Universidad Carlos III de Madrid in Spain, where he also received the Alumni Excellence Award. Legend has it that he used to have fun with antennas and electromagnetic sensors.

Myles Foley

Myles Foley

Ph.D. Student in Renforcement Learning for Cyber Security at the DoC.

Myles is a PhD student in the Security & Machine Learning (SML) Lab at Imperial under the supervision of Dr. Maffeis. He received his MEng from University College London in Electronic Engineering with Computer Science, earning the ‘Outstanding MEng Graduating Student’ prize. Myles’ research is focused at novel - and exciting - ways of applying reinforcement learning to problems in cyber security.

Eman Maali

Eman Maali

Ph.D. Student in IoT security at the DoC

Emaan is a fourth-year Ph.D. candidate at Adaptive Emergent Systems Engineering Laboratory (AESE) at the Department of Computing at Imperial. She is working under the supervision of Professor Julie McCann. Her research interest is in the field of secured IoT environments. In 2017, she completed her MSc in Electromagnetic Sensor Networks, at the University of Birmingham. The focus of the Masters was on electromagnetic, antennas, propagation, computer communications networks, and RF and microwave engineering. Moreover, she completed her BA in Computer Systems Engineering from Birzeit University in Palestine.

Dominika Woszczyk

Dominika Woszczyk

Ph.D. Student in Speech Processing and NLP within DoC

Dominika is a PhD Student working on Security and Voice Services under the supervision of Dr. Soteris Demetriou. She studies speech processing and NLP techniques to identifying privacy issues and building defenses. She also Postgraduate president of Women and Non-Binary Individuals in Computing (WNBIC) at Imperial and PhD Representative of her cohort and co-organizer of Imperial Computing Conference (ICC).




See you there