158 citations · 271 across the 18 of their papers we have counts for
10 papers · 1 filter
Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks
Pranav Dahiya, Ilia Shumailov, Ross Anderson
Randomness supports many critical functions in the field of machine learning (ML) including optimisation, data selection, privacy, and security. ML systems outsource the task of ge…
The Curse of Recursion: Training on Generated Data Makes Models Forget
Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao +3
Stable Diffusion revolutionised image creation from descriptive text. GPT-2, GPT-3(.5) and GPT-4 demonstrated astonishing performance across a variety of language tasks. ChatGPT in…
ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
Eleanor Clifford, Ilia Shumailov, Yiren Zhao +2
Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors…
Markpainting: Adversarial Machine Learning meets Inpainting
David Khachaturov, Ilia Shumailov, Yiren Zhao +2
Inpainting is a learned interpolation technique that is based on generative modeling and used to populate masked or missing pieces in an image; it has wide applications in picture…
Manipulating SGD with Data Ordering Attacks
Ilia Shumailov, Zakhar Shumaylov, Dmitry Kazhdan +4
Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained…
Sponge Examples: Energy-Latency Attacks on Neural Networks
Ilia Shumailov, Yiren Zhao, Daniel Bates +3
The high energy costs of neural network training and inference led to the use of acceleration hardware such as GPUs and TPUs. While this enabled us to train large-scale neural netw…
Towards Certifiable Adversarial Sample Detection
Ilia Shumailov, Yiren Zhao, Robert Mullins +1
Convolutional Neural Networks (CNNs) are deployed in more and more classification systems, but adversarial samples can be maliciously crafted to trick them, and are becoming a real…
Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information
Yiren Zhao, Ilia Shumailov, Han Cui +3
Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples c…
Sitatapatra: Blocking the Transfer of Adversarial Samples
Ilia Shumailov, Xitong Gao, Yiren Zhao +3
Convolutional Neural Networks (CNNs) are widely used to solve classification tasks in computer vision. However, they can be tricked into misclassifying specially crafted `adversari…
The Taboo Trap: Behavioural Detection of Adversarial Samples
Ilia Shumailov, Yiren Zhao, Robert Mullins +1
Deep Neural Networks (DNNs) have become a powerful toolfor a wide range of problems. Yet recent work has found an increasing variety of adversarial samplesthat can fool them. Most…