1 citations · 1 across the 4 of their papers we have counts for
5 papers
Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models
Lucas Beerens, Desmond J. Higham
We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiri…
Rethinking the Vulnerability of Concept Erasure and a New Method
Alex D. Richardson, Kaicheng Zhang, Lucas Beerens +1
The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In…
Deceptive Diffusion: Generating Synthetic Adversarial Examples
Lucas Beerens, Catherine F. Higham, Desmond J. Higham
We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb…
Vulnerability Analysis of Transformer-based Optical Character Recognition to Adversarial Attacks
Lucas Beerens, Desmond J. Higham
Recent advancements in Optical Character Recognition (OCR) have been driven by transformer-based models. OCR systems are critical in numerous high-stakes domains, yet their vulnera…
Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning
Lucas Beerens, Desmond J. Higham
Deep neural networks are capable of state-of-the-art performance in many classification tasks. However, they are known to be vulnerable to adversarial attacks -- small perturbation…