2 papers
cs.LG2023
Investigating Human-Identifiable Features Hidden in Adversarial Perturbations
Dennis Y. Menn, Tzu-hsun Feng, Sriram Vishwanath +1
Neural networks perform exceedingly well across various machine learning tasks but are not immune to adversarial perturbations. This vulnerability has implications for real-world a…
cs.LG2022
Searching for the Essence of Adversarial Perturbations
Dennis Y. Menn, Tzu-hsun Feng, Hung-yi Lee
Neural networks have demonstrated state-of-the-art performance in various machine learning fields. However, the introduction of malicious perturbations in input data, known as adve…