Con-Detect: Detecting adversarially perturbed natural language inputs to deep classifiers through holistic analysis
Deep Learning (DL) algorithms have shown wonders in many Natural Language Processing (NLP) tasks such as language-to-language translation, spam filtering, fake-news detection, and comprehension understanding. However, research has shown that the adversarial vulnerabilities of deep learning networks...
محفوظ في:
| المؤلف الرئيسي: | Hassan, Ali (author) |
|---|---|
| مؤلفون آخرون: | Khan, Muhammad Suleman (author), AlGhadhban, Amer (author), Alazmi, Meshari (author), Alzamil, Ahmed (author), Al-utaibi, Khaled (author), Qadir, Junaid (author) |
| التنسيق: | article |
| منشور في: |
2023
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | http://dx.doi.org/10.1016/j.cose.2023.103367 https://www.sciencedirect.com/science/article/pii/S0167404823002778 http://hdl.handle.net/10576/65987 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
مواد مشابهة
-
Con-Detect: Detecting Adversarially Perturbed Natural Language Inputs to Deep Classifiers Through Holistic Analysis
حسب: Hassan Ali (3348749)
منشور في: (2023) -
Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset
حسب: Abdalgawad, Nada
منشور في: (2021) -
Ten years of generative adversarial nets (GANs): a survey of the state-of-the-art
حسب: Chakraborty, Tanujit
منشور في: (2024) -
A3T: accuracy aware adversarial training
حسب: Enes Altinisik (17725956)
منشور في: (2023) -
Tamp-X: Attacking explainable natural language classifiers through tampered activations
حسب: Hassan Ali (3348749)
منشور في: (2022)