Picture for William Hackett

William Hackett

Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization

Add code
Sep 20, 2023
Viaarxiv icon

Model Leeching: An Extraction Attack Targeting LLMs

Sep 19, 2023
Figure 1 for Model Leeching: An Extraction Attack Targeting LLMs
Figure 2 for Model Leeching: An Extraction Attack Targeting LLMs
Figure 3 for Model Leeching: An Extraction Attack Targeting LLMs
Figure 4 for Model Leeching: An Extraction Attack Targeting LLMs
Viaarxiv icon

PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models

Sep 13, 2022
Figure 1 for PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models
Figure 2 for PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models
Figure 3 for PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models
Figure 4 for PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models
Viaarxiv icon