158 citations · 271 across the 18 of their papers we have counts for
7 papers · 1 filter
When Vision Fails: Text Attacks Against ViT and OCR
Nicholas Boucher, Jenny Blessing, Ilia Shumailov +2
Text-based machine learning models are vulnerable to an emerging class of Unicode-based adversarial examples capable of tricking a model into misreading text with potentially disas…
Boosting Big Brother: Attacking Search Engines with Encodings
Nicholas Boucher, Luca Pajola, Ilia Shumailov +2
Search engines are vulnerable to attacks against indexing and searching via text encoding manipulation. By imperceptibly perturbing text using uncommon encoded representations, adv…
Hey Alexa what did I just type? Decoding smartphone sounds with a voice assistant
Almos Zarandy, Ilia Shumailov, Ross Anderson
Voice assistants are now ubiquitous and listen in on our everyday lives. Ever since they became commercially available, privacy advocates worried that the data they collect can be…
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…
BatNet: Data transmission between smartphones over ultrasound
Almos Zarandy, Ilia Shumailov, Ross Anderson
In this paper, we present BatNet, a data transmission mechanism using ultrasound signals over the built-in speakers and microphones of smartphones. Using phase shift keying with an…
Hearing your touch: A new acoustic side channel on smartphones
Ilia Shumailov, Laurent Simon, Jeff Yan +1
We present the first acoustic side-channel attack that recovers what users type on the virtual keyboard of their touch-screen smartphone or tablet. When a user taps the screen with…
To compress or not to compress: Understanding the Interactions between Adversarial Attacks and Neural Network Compression
Yiren Zhao, Ilia Shumailov, Robert Mullins +1
As deep neural networks (DNNs) become widely used, pruned and quantised models are becoming ubiquitous on edge devices; such compressed DNNs are popular for lowering computational…