Ilia Shumailov
Ilia Shumailov
RS DeepMind, JRF Christ Church, University of Oxford; PhD, University of Cambridge; Fellow, Vector
Verifierad e-postadress på cl.cam.ac.uk - Startsida
Citeras av
Citeras av
The Curse of Recursion: Training on Generated Data Makes Models Forget
I Shumailov, Z Shumaylov, Y Zhao, Y Gal, N Papernot, R Anderson
https://arxiv.org/abs/2305.17493, 2023
When the Curious Abandon Honesty: Federated Learning Is Not Private
F Boenisch, A Dziedzic, R Schuster, AS Shamsabadi, I Shumailov, ...
8th IEEE European Symposium on Security and Privacy (EuroS&P 2023), 2021
Bad characters: Imperceptible NLP attacks
N Boucher, I Shumailov, R Anderson, N Papernot
2022 IEEE Symposium on Security and Privacy (SP), 1987-2004, 2022
Sponge Examples: Energy-Latency Attacks on Neural Networks
I Shumailov, Y Zhao, D Bates, N Papernot, R Mullins, R Anderson
6th IEEE European Symposium on Security and Privacy (EuroS&P 2021), 2020
On the necessity of auditable algorithmic definitions for machine unlearning
A Thudi, H Jia, I Shumailov, N Papernot
31st USENIX Security Symposium (USENIX Security 22), 4007-4022, 2022
Manipulating SGD with data ordering attacks
I Shumailov, Z Shumaylov, D Kazhdan, Y Zhao, N Papernot, MA Erdogdu, ...
35th Conference on Neural Information Processing Systems (NeurIPS), 2021
Hearing your touch: A new acoustic side channel on smartphones
I Shumailov, L Simon, J Yan, R Anderson
arXiv preprint arXiv:1903.11137, 2019
Turning Up the Dial: the Evolution of a Cybercrime Market Through Set-up, Stable, and Covid-19 Eras
AV Vu, J Hughes, I Pete, B Collier, YT Chua, I Shumailov, A Hutchings
ACM Internet Measurement Conference (IMC 2020), 551-566, 2020
To compress or not to compress: Understanding the Interactions between Adversarial Attacks and Neural Network Compression
Y Zhao, I Shumailov, R Mullins, R Anderson
Conference on Machine Learning and Systems (SysML 2018), 2018
Mapping the Underground: Supervised Discovery of Cybercrime Supply Chains
R Bhalerao, M Aliapoulios, I Shumailov, S Afroz, D McCoy
Symposium on Electronic Crime Research (eCrime 2019), 2019
Making Bitcoin Legal
R Anderson, I Shumailov, M Ahmed
International Workshop on Security Protocols (SPW 2018), 2018
Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information
Y Zhao, I Shumailov, H Cui, X Gao, R Mullins, R Anderson
Dependable and Secure Machine Learning (DSML 2020), 2019
Bitcoin Redux
R Anderson, I Shumailov, M Ahmed, A Rietmann
Workshop on the Economics of Information Security (WEIS 2018), 2018
Tendrils of crime: Visualizing the diffusion of stolen bitcoins
M Ahmed, I Shumailov, R Anderson
Graphical Models for Security: 5th International Workshop, GraMSec 2018 …, 2019
Not my deepfake: Towards plausible deniability for machine-generated media
B Zhang, JP Zhou, I Shumailov, N Papernot
arXiv preprint arXiv:2008.09194, 2020
Towards More Robust Keyword Spotting for Voice Assistants
S Ahmed, I Shumailov, N Papernot, K Fawaz
31st USENIX Security Symposium (USENIX Security 22), 2022
On the Limitations of Stochastic Pre-processing Defenses
Y Gao, I Shumailov, K Fawaz, N Papernot
36th Conference on Neural Information Processing Systems (NeurIPS), 2022
Computational analysis of valence and arousal in virtual reality gaming using lower arm electromyograms
I Shumailov, H Gunes
2017 Seventh International Conference on Affective Computing and Intelligent …, 2017
Towards certifiable adversarial sample detection
I Shumailov, Y Zhao, R Mullins, R Anderson
13th ACM Workshop on Artificial Intelligence and Security (AISec 2020), 13-24, 2020
The taboo trap: Behavioural detection of adversarial samples
I Shumailov, Y Zhao, R Mullins, R Anderson
arXiv preprint arXiv:1811.07375, 2018
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20