← Search

Amir Rahmati

2 accepted papers

2022

Accelerating Certified Robustness Training via Knowledge Transfer

NeurIPS 2022accept

Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Although numerous state-of-the-art certified training methods have been developed, they are computationally expensive and sc…

2018

Robust Physical-World Attacks on Deep Learning Visual Classification

CVPR 2018poster

Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input. Given that that emerging physical systems are using DNNs in safety-critical situations, adversarial examples could mislea…

Cited by 2927SourcePDFScholar