Using Random Perturbations to Mitigate Adversarial Attacks on NLP Models
A Swenor - Proceedings of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
Deep learning models have excelled in solving many problems in Natural Language
Processing, but are susceptible to extensive vulnerabilities. We offer a solution to this …
Processing, but are susceptible to extensive vulnerabilities. We offer a solution to this …
[PDF][PDF] Using Random Perturbations to Mitigate Adversarial Attacks on NLP Models
A Swenor, J Kalita - Deep Learning, 2021 - faculty.uccs.edu
Deep learning models have excelled in solving many difficult problems in Natural Language
Processing (NLP), but it has been demonstrated that such models are susceptible to …
Processing (NLP), but it has been demonstrated that such models are susceptible to …
[PDF][PDF] Using Random Perturbations to Mitigate Adversarial Attacks on NLP Models
A Swenor - 2022 - ojs.aaai.org
Deep learning models have excelled in solving many problems in Natural Language
Processing, but are susceptible to extensive vulnerabilities. We offer a solution to this …
Processing, but are susceptible to extensive vulnerabilities. We offer a solution to this …
[PDF][PDF] Using Random Perturbations to Mitigate Adversarial Attacks on NLP Models
A Swenor - 2022 - cdn.aaai.org
Deep learning models have excelled in solving many problems in Natural Language
Processing, but are susceptible to extensive vulnerabilities. We offer a solution to this …
Processing, but are susceptible to extensive vulnerabilities. We offer a solution to this …
Using Random Perturbations to Mitigate Adversarial Attacks on Sentiment Analysis Models
A Swenor, J Kalita - arXiv preprint arXiv:2202.05758, 2022 - arxiv.org
Attacks on deep learning models are often difficult to identify and therefore are difficult to
protect against. This problem is exacerbated by the use of public datasets that typically are …
protect against. This problem is exacerbated by the use of public datasets that typically are …
Using Random Perturbations to Mitigate Adversarial Attacks on Sentiment Analysis Models
A Swenor, J Kalita - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Attacks on deep learning models are often difficult to identify and therefore are difficult to
protect against. This problem is exacerbated by the use of public datasets that typically are …
protect against. This problem is exacerbated by the use of public datasets that typically are …
[PDF][PDF] Using Random Perturbations to Mitigate Adversarial Attacks on NLP Models
A Swenor - 2022 - scholar.archive.org
Deep learning models have excelled in solving many problems in Natural Language
Processing, but are susceptible to extensive vulnerabilities. We offer a solution to this …
Processing, but are susceptible to extensive vulnerabilities. We offer a solution to this …
Using Random Perturbations to Mitigate Adversarial Attacks on Sentiment Analysis Models
A Swenor, J Kalita - … of the 18th International Conference on …, 2021 - aclanthology.org
Attacks on deep learning models are often difficult to identify and therefore are difficult to
protect against. This problem is exacerbated by the use of public datasets that typically are …
protect against. This problem is exacerbated by the use of public datasets that typically are …