August 15, 2019
Adversarial examples, perturbations to the input of a model that elicit large changes in the output, have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models. However, these perturbations only indicate weaknesses in the model if they do not change the input so significantly that it legitimately result in changes in the expected output. This fact that has largely been ignored in the evaluations of the growing body of related literature. Using the example of untargeted attacks on machine translation (MT), we propose a new evaluation framework for adversarial attacks on seq2seq models that takes the semantic equivalence of the pre- and post-perturbation input into account. Using this framework, we demonstrate that existing methods may not preserve meaning in general, breaking the aforementioned assumption that source side perturbations should not result in changes in the expected output. We further use this framework to demonstrate that adding additional constraints on attacks allows for adversarial perturbations that are more meaning-preserving, but nonetheless largely change the output sequence. Finally, we show that performing untargeted adversarial training with meaning-preserving attacks is beneficial to the model in terms of adversarial robustness, without hurting test performance.
Publisher
NAACL
April 17, 2025
Ansong Ni, Ruta Desai, Yang Li, Xinjie Lei, Dong Wang, Ramya Raghavendra, Gargi Ghosh, Daniel Li (FAIR), Asli Celikyilmaz
April 17, 2025
April 17, 2025
Paul McVay, Sergio Arnaud, Ada Martin, Arjun Majumdar, Krishna Murthy Jatavallabhula, Phillip Thomas, Ruslan Partsey, Daniel Dugas, Abha Gejji, Alexander Sax, Vincent-Pierre Berges, Mikael Henaff, Ayush Jain, Ang Cao, Ishita Prasad, Mrinal Kalakrishnan, Mike Rabbat, Nicolas Ballas, Mido Assran, Oleksandr Maksymets, Aravind Rajeswaran, Franziska Meier
April 17, 2025
April 14, 2025
Yeongmin Kim, Sotiris Anagnostidis, Yuming Du, Edgar Schoenfeld, Jonas Kohler, Markos Georgopoulos, Albert Pumarola, Ali Thabet, Artsiom Sanakoyeu
April 14, 2025
March 25, 2025
Wassim (Wes) Bouaziz, El Mahdi El Mhamdi, Nicolas Usunier
March 25, 2025
Foundational models
Our approach
Latest news
Foundational models