Benjamin Rubinstein

Differential Privacy (1) Privacy (1)

backdoor attack (5) trigger detection (2) adversarial learning (2) neural machine translation (2) convex optimization (1) text classification (1) model security (1) word alignment (1) variational inference (1) multilingual machine translation (1) tensor decomposition (1) outlier detection (1) label aggregation (1) query complexity (1) adversarial attack (1) low-resource language (1) data augmentation (1) bias mitigation (1) language model (1) data poisoning (1)