Matt Fredrikson

adversarial robustness (5) adversarial attack (3) neural network (2) large language model (2) jailbreak attack (2) certified robustness (2) adversarial example (2) symbolic reasoning (1) algorithmic fairness (1) adversarial learning (1) ai safety (1) constrained optimization (1) safety alignment (1) model alignment (1) feature attribution (1) sparse optimization (1) neural network interpretability (1) linear regression (1) gradient descent (1) adversarial training (1)