Security enhanced sentence similarity computing model based on convolutional neural network
Deep learning model shows great advantages in various fields. However, researchers pay
attention to how to improve the accuracy of the model, while ignoring the security …
attention to how to improve the accuracy of the model, while ignoring the security …
Chinese adversarial examples generation approach with multi-strategy based on semantic
H Ou, L Yu, S Tian, X Chen - Knowledge and Information Systems, 2022 - Springer
Recent studies have shown that after adding small perturbations that are imperceptible to
humans, deep neural networks (DNNs) with good performance and popular application are …
humans, deep neural networks (DNNs) with good performance and popular application are …
Textual Adversarial training of machine learning model for resistance to adversarial examples
Deep neural networks provide good performance for image recognition, speech recognition,
text recognition, and pattern recognition. However, such networks are vulnerable to attack by …
text recognition, and pattern recognition. However, such networks are vulnerable to attack by …
Enhancing neural models with vulnerability via adversarial attack
Abstract Natural Language Sentence Matching (NLSM) serves as the core of many natural
language processing tasks. 1) Most previous work develops a single specific neural model …
language processing tasks. 1) Most previous work develops a single specific neural model …
Similarity analysis of law documents based on Word2vec
C Xia, T He, W Li, Z Qin, Z Zou - 2019 IEEE 19th International …, 2019 - ieeexplore.ieee.org
With the increasing demand for computer-assisted wisdom in justice, deep learning has
gradually become an effective means of helping intelligent justice. The similarity analysis of …
gradually become an effective means of helping intelligent justice. The similarity analysis of …
Exploring security vulnerabilities of deep learning models by adversarial attacks
Nowadays, deep learning models play an important role in a variety of scenarios, such as
image classification, natural language processing, and speech recognition. However, deep …
image classification, natural language processing, and speech recognition. However, deep …
Hybridization between neural computing and nature-inspired algorithms for a sentence similarity model based on the attention mechanism
Sentence similarity analysis has been applied in many fields, such as machine translation,
the question answering system, and voice customer service. As a basic task of natural …
the question answering system, and voice customer service. As a basic task of natural …
WordRevert: adversarial examples defence method for Chinese text classification
E Xu, X Zhang, Y Wang, S Zhang, L Lu, L Xu - IEEE Access, 2022 - ieeexplore.ieee.org
Adversarial examples can evade the detection of text classification models based on Deep
Neural Networks (DNNs), thus posing a potential security threat to the system. To address …
Neural Networks (DNNs), thus posing a potential security threat to the system. To address …
Adversarial examples generation approach for tendency classification on Chinese texts
王文琦， 汪润， 王丽娜， 唐奔宵 - Journal of Software, 2019 - jos.org.cn
研究表明, 在深度神经网络 (DNN) 的输入中添加小的扰动信息, 能够使得 DNN 出现误判,
这种攻击被称为对抗样本攻击. 而对抗样本攻击也存在于基于 DNN 的中文文本的情感倾向性 …
这种攻击被称为对抗样本攻击. 而对抗样本攻击也存在于基于 DNN 的中文文本的情感倾向性 …
Aliasing black box adversarial attack with joint self-attention distribution and confidence probability
Deep neural networks (DNNs) are vulnerable to adversarial attacks, in which a small
perturbation to samples can cause misclassification. However, how to select important …
perturbation to samples can cause misclassification. However, how to select important …