The triggers that open the NLP model backdoors are hidden in the adversarial samples-Reference-Cited by-同舟云学术

The triggers that open the NLP model backdoors are hidden in the adversarial samples

Published:2022-07 Issue: Volume:118 Page:102730
ISSN:0167-4048
Container-title:Computers & Security
language:en
Short-container-title:Computers & Security

Author:

Shao Kun^ORCID,Zhang Yu,Yang Junan,Li Xiaoshuai^ORCID,Liu Hui

Publisher

Elsevier BV

Subject

Law,General Computer Science

Reference37 articles.

1. Generating natural language adversarial examples;Alzantot;Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing,2018

2. Universal adversarial attacks on text classifiers;Behjati;2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),2019

3. Towards evaluating the robustness of neural networks;Carlini;2017 IEEE symposium on security and privacy,2017

4. Poba-ga: perturbation optimized black-box adversarial attacks via genetic algorithm;Chen;Computers & Security,2019

Cited by 12 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Adversarial Attacks and Defenses in Deep Learning-Based Computer Vision Systems;2024 IEEE 4th International Conference on Electronic Technology, Communication and Information (ICETCI);2024-05-24

2. Comprehensive framework for implementing blockchain-enabled federated learning and full homomorphic encryption for chatbot security system;Cluster Computing;2024-05-12

3. Backdoor Breakthrough;Advances in Medical Technologies and Clinical Practice;2024-04-12

4. Towards a unified framework for imperceptible textual attacks;Applied Intelligence;2024-02

5. Implementing a Multitarget Backdoor Attack Algorithm Based on Procedural Noise Texture Features;IEEE Access;2024