paper-with-me

Papers

On Meaning-Preserving Adversarial Perturbations for Sequence-to-Sequence Models

2019-05-01 · ICLR 2019 5 · Paul Michel, Graham Neubig, Xi-An Li, Juan Miguel Pino

Adversarial examples have been shown to be an effective way of assessing the robustness of neural sequence-to-sequence (seq2seq) models, by applying perturbations to the input of a model leading to large degradation in performance. However, these perturbations are only indicative of a weakness in the model if they do not change the semantics of the input in a way that would change the expected output. Using the example of machine translation (MT), we propose a new evaluation framework for adversarial attacks on seq2seq models taking meaning preservation into account and demonstrate that existing methods may not preserve meaning in general. Based on these findings, we propose new constraints for attacks on word-based MT systems and show, via human and automatic evaluation, that they produce more semantically similar adversarial inputs. Furthermore, we show that performing adversarial training with meaning-preserving attacks is beneficial to the model in terms of adversarial robustness without hurting test performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models

2019-03-15 · NAACL 2019 6 · Paul Michel, Xi-An Li, Graham Neubig, Juan Miguel Pino

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. Howe…

Adversarial RobustnessMachine Translation

Robust Tracking against Adversarial Attacks

2020-07-20 · ECCV 2020 8 · Shuai Jia, Chao Ma, Yibing Song, Xiaokang Yang

While deep convolutional neural networks (CNNs) are vulnerable to adversarial attacks, considerably few efforts have been paid to construct robust deep tracking algorithms against adversarial attacks. Current studies on …

Adversarial Attack

Semantic Robustness of Models of Source Code

2020-02-07 · Goutham Ramakrishnan, Jordan Henkel, Zi Wang, Aws Albarghouthi 외

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to sou…

Protein Folding Neural Networks Are Not Robust

2021-09-09 · Sumit Kumar Jha, Arvind Ramanathan, Rickard Ewetz, Alvaro Velasquez 외

Deep neural networks such as AlphaFold and RoseTTAFold predict remarkably accurate structures of proteins compared to other algorithmic approaches. It is known that biologically small perturbations in the protein sequenc…

Adversarial AttackProtein Folding

SAR-GPA: SAR Generation Perturbation Algorithm

2022-01-19 · ACM 2022 1 · Zhe Liu, Weijie Xia, Yongzhen Lei

The deep learning is widely used in optical image and synthetic aperture radar (SAR) image. Current academic research shows that adversarial perturbation can effectively attack the deep learning network in optical ima…