Picture for Desmond J. Higham

Desmond J. Higham

Deceptive Diffusion: Generating Synthetic Adversarial Examples

Add code
Jun 28, 2024
Figure 1 for Deceptive Diffusion: Generating Synthetic Adversarial Examples
Figure 2 for Deceptive Diffusion: Generating Synthetic Adversarial Examples
Figure 3 for Deceptive Diffusion: Generating Synthetic Adversarial Examples
Figure 4 for Deceptive Diffusion: Generating Synthetic Adversarial Examples
Viaarxiv icon

Stealth edits for provably fixing or attacking large language models

Add code
Jun 18, 2024
Figure 1 for Stealth edits for provably fixing or attacking large language models
Figure 2 for Stealth edits for provably fixing or attacking large language models
Figure 3 for Stealth edits for provably fixing or attacking large language models
Figure 4 for Stealth edits for provably fixing or attacking large language models
Viaarxiv icon

Diffusion Models for Generative Artificial Intelligence: An Introduction for Applied Mathematicians

Add code
Dec 21, 2023
Viaarxiv icon

Vulnerability Analysis of Transformer-based Optical Character Recognition to Adversarial Attacks

Add code
Nov 28, 2023
Viaarxiv icon

The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning

Add code
Sep 13, 2023
Viaarxiv icon

How adversarial attacks can disrupt seemingly stable accurate classifiers

Add code
Sep 07, 2023
Figure 1 for How adversarial attacks can disrupt seemingly stable accurate classifiers
Figure 2 for How adversarial attacks can disrupt seemingly stable accurate classifiers
Figure 3 for How adversarial attacks can disrupt seemingly stable accurate classifiers
Figure 4 for How adversarial attacks can disrupt seemingly stable accurate classifiers
Viaarxiv icon

Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: Application to stochastic coordinate descent

Add code
Sep 05, 2023
Figure 1 for Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: Application to stochastic coordinate descent
Figure 2 for Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: Application to stochastic coordinate descent
Figure 3 for Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: Application to stochastic coordinate descent
Viaarxiv icon

Can We Rely on AI?

Add code
Aug 29, 2023
Figure 1 for Can We Rely on AI?
Viaarxiv icon

Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning

Add code
Jun 05, 2023
Figure 1 for Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning
Figure 2 for Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning
Figure 3 for Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning
Figure 4 for Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning
Viaarxiv icon

The Feasibility and Inevitability of Stealth Attacks

Add code
Jun 26, 2021
Figure 1 for The Feasibility and Inevitability of Stealth Attacks
Figure 2 for The Feasibility and Inevitability of Stealth Attacks
Figure 3 for The Feasibility and Inevitability of Stealth Attacks
Figure 4 for The Feasibility and Inevitability of Stealth Attacks
Viaarxiv icon