TY - GEN
T1 - KBAA
T2 - 7th International Conference on Dependable Systems and Their Applications, DSA 2020
AU - Guo, Shudi
AU - Wang, Shihai
AU - Liu, Bin
AU - Shi, Tengfei
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11
Y1 - 2020/11
N2 - The adversarial example generation algorithm is currently a very popular algorithm for deceiving machine learning. The main method is to change the original sample in a way that is almost imperceptible to the user, and cause an obvious error in the result returned by the model. At present, there are many adversarial algorithms for computer vision, but there are few for NLP models, and there is almost no algorithm for Question Answer task. This paper designs a framework of adversarial example generation algorithm KBAA(Knowledge-based Adversarial Attack), which is a black box attack, and is against KBQA (Knowledge-based Question Answer). By extracting the knowledge graph of the original sample (attribute value is null, Entity-Attribute-(null)), the algorithm chooses the more important one of Entity and Attribute in the original sample and generates an adversarial example in order to deceive the KBQA model.
AB - The adversarial example generation algorithm is currently a very popular algorithm for deceiving machine learning. The main method is to change the original sample in a way that is almost imperceptible to the user, and cause an obvious error in the result returned by the model. At present, there are many adversarial algorithms for computer vision, but there are few for NLP models, and there is almost no algorithm for Question Answer task. This paper designs a framework of adversarial example generation algorithm KBAA(Knowledge-based Adversarial Attack), which is a black box attack, and is against KBQA (Knowledge-based Question Answer). By extracting the knowledge graph of the original sample (attribute value is null, Entity-Attribute-(null)), the algorithm chooses the more important one of Entity and Attribute in the original sample and generates an adversarial example in order to deceive the KBQA model.
KW - KBQA task
KW - Knowledge based adversarial attack
KW - NLP model
KW - adversarial example generation
UR - https://www.scopus.com/pages/publications/85100577390
U2 - 10.1109/DSA51864.2020.00056
DO - 10.1109/DSA51864.2020.00056
M3 - 会议稿件
AN - SCOPUS:85100577390
T3 - Proceedings - 2020 7th International Conference on Dependable Systems and Their Applications, DSA 2020
SP - 313
EP - 318
BT - Proceedings - 2020 7th International Conference on Dependable Systems and Their Applications, DSA 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 28 November 2020 through 29 November 2020
ER -