research
∙
08/23/2023
SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
Machine Learning (ML) systems are vulnerable to adversarial examples, pa...
share
research
∙
07/20/2023
LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
Large language models (LLMs) have exhibited impressive capabilities in c...
research
∙
07/01/2023
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
Differentially private stochastic gradient descent (DP-SGD) is the canon...
research
∙
06/24/2023
Machine Learning needs its own Randomness Standard: Randomised Smoothing and PRNG-based attacks
Randomness supports many critical functions in the field of machine lear...
research
∙
06/12/2023
When Vision Fails: Text Attacks Against ViT and OCR
While text-based machine learning models that operate on visual inputs o...
research
∙
05/27/2023
The Curse of Recursion: Training on Generated Data Makes Models Forget
Stable Diffusion revolutionised image creation from descriptive text. GP...
research
∙
04/27/2023
Boosting Big Brother: Attacking Search Engines with Encodings
Search engines are vulnerable to attacks against indexing and searching ...
research
∙
04/07/2023
Revisiting Automated Prompting: Are We Actually Doing Better?
Current literature demonstrates that Large Language Models (LLMs) are gr...
research
∙
01/09/2023
Is Federated Learning a Practical PET Yet?
Federated learning (FL) is a framework for users to jointly train a mach...
research
∙
10/02/2022
DARTFormer: Finding The Best Type Of Attention
Given the wide and ever growing range of different efficient Transformer...
research
∙
10/02/2022
Wide Attention Is The Way Forward For Transformers
The Transformer is an extremely powerful and prominent deep learning arc...
research
∙
09/30/2022
ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
Early backdoor attacks against machine learning set off an arms race in ...
research
∙
09/29/2022
Augmentation Backdoors
Data augmentation is used extensively to improve model generalisation. H...
research
∙
09/22/2022
In Differential Privacy, There is Truth: On Vote Leakage in Ensemble Private Learning
When learning from sensitive data, care must be taken to ensure that tra...
research
∙
07/01/2022
Efficient Adversarial Training With Data Pruning
Neural networks are susceptible to adversarial examples-small input pert...
research
∙
06/19/2022
On the Limitations of Stochastic Pre-processing Defenses
Defending against adversarial examples remains an open problem. A common...
research
∙
06/15/2022
Architectural Backdoors in Neural Networks
Machine learning is vulnerable to adversarial manipulation. Previous lit...
research
∙
02/24/2022
Bounding Membership Inference
Differential Privacy (DP) is the de facto standard for reasoning about t...
research
∙
02/09/2022
Model Architecture Adaption for Bayesian Neural Networks
Bayesian Neural Networks (BNNs) offer a mathematically grounded framewor...
research
∙
02/06/2022
Pipe Overflow: Smashing Voice Authentication for Fun and Profit
Recent years have seen a surge of popularity of acoustics-enabled person...
research
∙
12/06/2021
When the Curious Abandon Honesty: Federated Learning Is Not Private
In federated learning (FL), data does not leave personal devices when th...
research
∙
11/08/2021
ExtremeBB: Enabling Large-Scale Research into Extremism, the Manosphere and Their Correlation by Online Forum Data
Online extremism is a growing and pernicious problem, and increasingly l...
research
∙
10/22/2021
On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning
Machine unlearning, i.e. having a model forget about some of its trainin...
research
∙
09/10/2021
Rapid Model Architecture Adaption for Meta-Learning
Network Architecture Search (NAS) methods have recently gathered much at...
research
∙
06/18/2021
Bad Characters: Imperceptible NLP Attacks
Several years of research have shown that machine-learning systems are v...
research
∙
06/01/2021
Markpainting: Adversarial Machine Learning meets Inpainting
Inpainting is a learned interpolation technique that is based on generat...
research
∙
04/19/2021
Manipulating SGD with Data Ordering Attacks
Machine learning is vulnerable to a wide variety of different attacks. I...
research
∙
12/01/2020
Hey Alexa what did I just type? Decoding smartphone sounds with a voice assistant
Voice assistants are now ubiquitous and listen in on our everyday lives....
research
∙
11/22/2020
Nudge Attacks on Point-Cloud DNNs
The wide adaption of 3D point-cloud data in safety-critical applications...
research
∙
08/20/2020
Not My Deepfake: Towards Plausible Deniability for Machine-Generated Media
Progress in generative modelling, especially generative adversarial netw...
research
∙
08/01/2020
BatNet: Data transmission between smartphones over ultrasound
In this paper, we present BatNet, a data transmission mechanism using ul...
research
∙
06/25/2020
Snitches Get Stitches: On The Difficulty of Whistleblowing
One of the most critical security protocol problems for humans is when y...
research
∙
06/05/2020
Sponge Examples: Energy-Latency Attacks on Neural Networks
The high energy costs of neural network training and inference led to th...
research
∙
02/20/2020
Towards Certifiable Adversarial Sample Detection
Convolutional Neural Networks (CNNs) are deployed in more and more class...
research
∙
09/06/2019
Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information
Recent research on reinforcement learning has shown that trained agents ...
research
∙
03/26/2019
Hearing your touch: A new acoustic side channel on smartphones
We present the first acoustic side-channel attack that recovers what use...
research
∙
01/23/2019
Sitatapatra: Blocking the Transfer of Adversarial Samples
Convolutional Neural Networks (CNNs) are widely used to solve classifica...
research
∙
01/07/2019
Tendrils of Crime: Visualizing the Diffusion of Stolen Bitcoins
The first six months of 2018 have seen cryptocurrency thefts of 761 mill...
research
∙
12/02/2018
Towards Automatic Discovery of Cybercrime Supply Chains
Cybercrime forums enable modern criminal entrepreneurs to collaborate wi...
research
∙
12/02/2018
Mapping the Underground: Towards Automatic Discovery of Cybercrime Supply Chains
Cybercrime forums enable modern criminal entrepreneurs to collaborate wi...
research
∙
11/18/2018
The Taboo Trap: Behavioural Detection of Adversarial Samples
Deep Neural Networks (DNNs) have become a powerful tool for a wide range...
research
∙
09/29/2018