University of Cambridge
15 JJ Thomson Avenue
Cambridge CB3 0FD
University phone number: (7)63616
Useful links: here
My name is Ilia and I am a PhD candidate under the supervision of Prof Ross Anderson. My interests lie in fields of DSP, Security and ML.
I can be contacted at: Ilia.Shumailov [at] cl [dot] cam [dot] ac [dot] uk
I very much enjoy methodological work and have a precious relationship with acousic research.
Publications and work in progress during the PhD years [so far]:
- Adversarial Reinforcement Learning: [mostly equal contributions with Yiren Zhao]
- Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information, currently under review for a publication. draft arxiv
- Towards efficient CNN defences: [mostly equal contributions with Yiren Zhao]
- Sitatapatra: Blocking the Transfer of Adversarial Samples, currently under review for a publication. draft arxiv
- The Taboo Trap: Behavioural Detection of Adversarial Samples, currently under review for a publication. draft arxiv
- To compress or not to compress: Understanding the Interactions between Adversarial Attacks and Neural Network Compression, SysML 2019 (Acceptance rate: ~16%), paper, poster, video
- Cryptocurrencies, Cryptocrime, Tracibility and Legality
- Cybercrime and the underground economy
- Acoustic side-channel attacks
- Hearing your touch: A new acoustic side channel on smartphones, currently under review for a publication. arxiv, poster
- Computational Analysis of Valence and Arousal in Virtual Reality Gaming using Lower Arm Electromyograms, ACII 2017, IEEExplore, poster
Big Projects I participate(d) in
I am supervising for:
So far I have supervised ~70 students in ~120 hours.
I run Hardware Security Reading group at the Computer Laboratory and manage the mailing list. If you want to be added to the list just reach out to me.
We run our meetings every Wednesday 13-14 in FW09.
I have supervised Part II students in the past.
I have a few Part II/Part III/MPhil thesis ideas in fields of signal processing for security purpose and adversarial machine learning.
To discuss potential supervision drop by my office GE14 or send me an email.
So far I had 3 Part II and 1 MPhil students. Those projects are already available internaly in Cambridge and I am trying to make them also available globaly.
Interesting News Articles