204 citations · 306 across the 21 of their papers we have counts for
29 papers
Revisiting Automated Prompting: Are We Actually Doing Better?
Yulin Zhou, Yiren Zhao, Ilia Shumailov +2
Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream task…
Dynamic Stashing Quantization for Efficient Transformer Training
Guo Yang, Daniel Lo, Robert Mullins +1
Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks. Unfortunately, the immense amount of computations and m…
Wide Attention Is The Way Forward For Transformers?
Jason Ross Brown, Yiren Zhao, Ilia Shumailov +1
The Transformer is an extremely powerful and prominent deep learning architecture. In this work, we challenge the commonly held belief in deep learning that going deeper is better,…
Revisiting Structured Dropout
Yiren Zhao, Oluwatomisin Dada, Xitong Gao +1
Large neural networks are often overparameterised and prone to overfitting, Dropout is a widely used regularization technique to combat overfitting and improve model generalization…
DARTFormer: Finding The Best Type Of Attention
Jason Ross Brown, Yiren Zhao, Ilia Shumailov +1
Given the wide and ever growing range of different efficient Transformer attention mechanisms, it is important to identify which attention is most effective when given a task. In t…
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…
Augmentation Backdoors
Joseph Rance, Yiren Zhao, Ilia Shumailov +1
Data augmentation is used extensively to improve model generalisation. However, reliance on external libraries to implement augmentation methods introduces a vulnerability into the…
Efficient Adversarial Training With Data Pruning
Maximilian Kaufmann, Yiren Zhao, Ilia Shumailov +2
Neural networks are susceptible to adversarial examples-small input perturbations that cause models to fail. Adversarial training is one of the solutions that stops adversarial exa…
Architectural Backdoors in Neural Networks
Mikel Bober-Irizar, Ilia Shumailov, Yiren Zhao +2
Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedur…
Muntjac -- Open Source Multicore RV64 Linux-capable SoC
Xuan Guo, Daniel Bates, Robert Mullins +1
Muntjac is an open-source collection of components which can be used to build a multicore, Linux-capable system-on-chip. This includes a 64-bit RISC-V core, a cache subsystem, and…
Model Architecture Adaption for Bayesian Neural Networks
Duo Wang, Yiren Zhao, Ilia Shumailov +1
Bayesian Neural Networks (BNNs) offer a mathematically grounded framework to quantify the uncertainty of model predictions but come with a prohibitive computation cost for both tra…
DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning
Robert Hönig, Yiren Zhao, Robert Mullins
Federated Learning (FL) is a powerful technique for training a model on a server with data from several clients in a privacy-preserving manner. In FL, a server sends the model to e…
Rapid Model Architecture Adaption for Meta-Learning
Yiren Zhao, Xitong Gao, Ilia Shumailov +2
Network Architecture Search (NAS) methods have recently gathered much attention. They design networks with better performance and use a much shorter search time compared to traditi…
Nudge Attacks on Point-Cloud DNNs
Yiren Zhao, Ilia Shumailov, Robert Mullins +1
The wide adaption of 3D point-cloud data in safety-critical applications such as autonomous driving makes adversarial samples a real threat. Existing adversarial attacks on point c…
Learned Low Precision Graph Neural Networks
Yiren Zhao, Duo Wang, Daniel Bates +3
Deep Graph Neural Networks (GNNs) show promising performance on a range of graph tasks, yet at present are costly to run and lack many of the optimisations applied to DNNs. We show…
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…
Accelerate Cycle-Level Full-System Simulation of Multi-Core RISC-V Systems with Binary Translation
Xuan Guo, Robert Mullins
It has always been difficult to balance the accuracy and performance of ISSs. RTL simulators or systems such as gem5 are used to execute programs in a cycle-accurate manner but are…
Probabilistic Dual Network Architecture Search on Graphs
Yiren Zhao, Duo Wang, Xitong Gao +3
We present the first differentiable Network Architecture Search (NAS) for Graph Neural Networks (GNNs). GNNs show promising performance on a wide range of tasks, but require a larg…
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…
Automatic Generation of Multi-precision Multi-arithmetic CNN Accelerators for FPGAs
Yiren Zhao, Xitong Gao, Xuan Guo +6
Modern deep Convolutional Neural Networks (CNNs) are computationally demanding, yet real applications often require high throughput and low latency. To help tackle these problems,…
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…
Fast TLB Simulation for RISC-V Systems
Xuan Guo, Robert Mullins
Address translation and protection play important roles in today's processors, supporting multiprocessing and enforcing security. Historically, the design of the address translatio…
Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs
Partha Maji, Andrew Mundy, Ganesh Dasika +3
The Winograd or Cook-Toom class of algorithms help to reduce the overall compute complexity of many modern deep convolutional neural networks (CNNs). Although there has been a lot…
Focused Quantization for Sparse CNNs
Yiren Zhao, Xitong Gao, Daniel Bates +2
Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs pose a chall…