2022

PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications

Garcia-soto, Diego, Chen, Huili, Koushanfar, Farinaz

Understand

Deep Neural Networks (DNNs) have been shown to be susceptible to Trojan attacks.

Neural Trojan is a type of targeted poisoning attack that embeds the backdoor into the victim and is activated by the trigger in the input space.
The increasing deployment of DNNs in critical systems and the surge of outsourcing DNN training (which makes Trojan attack easier) makes the detection of Trojan attacks necessary.
While Neural Trojan detection has been studied in the image domain, there is a lack of solutions in the NLP domain.

A. L. Maas, R. E. Daly, P. T. Pham, D. Huang, A. Y. Ng, and C. Potts, “Learning word vectors for sentiment analysis,” in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
2011
Earlier work this paper cites.
P. Rajpurkar, J. Zhang, K. Lopyrev, and P. Liang, “SQuAD: 100,000+ Questions for Machine Comprehension of Text,” arXiv e-prints
Original
2016
Earlier work this paper cites.
M. Bojarski, P. Yeres, A. Choromanska, K. Choromanski, B. Firner, L. Jackel, and U. Muller, “Explaining how a deep neural network trained with end-to-end learning steers a car,” arXiv preprint arXiv:1704.07911
Original
2017
Earlier work this paper cites.
T. Gu, B. Dolan-Gavitt, and S. Garg, “Badnets: Identifying vulnerabilities in the machine learning model supply chain,” arXiv preprint arXiv:1708.06733
Original
2017
Earlier work this paper cites.
Y. Liu, S. Ma, Y. Aafer, W.-C. Lee, J. Zhai, W. Wang, and X. Zhang, “Trojaning attack on neural networks,” 2017
2017
Earlier work this paper cites.

S. Ma and Y. Liu, “Nic: Detecting adversarial samples with neural network invariant checking,” in Proceedings of the 26th network and distributed system security symposium (NDSS 2019)
2019
Cited alongside, same era.
B. Wang, Y. Yao, S. Shan, H. Li, B. Viswanath, H. Zheng, and B. Y. Zhao, “Neural cleanse: Identifying and mitigating backdoor attacks in neural networks,” in 2019 IEEE Symposium on Security and Privacy (SP)
2019
Cited alongside, same era.
H. Chen, C. Fu, J. Zhao, and F. Koushanfar, “Deepinspect: A black-box trojan detection and mitigation framework for deep neural networks.,” in IJCAI
2019
Cited alongside, same era.
Y. Liu, W.-C. Lee, G. Tao, S. Ma, Y. Aafer, and X. Zhang, “Abs: Scanning neural networks for back-doors by artificial brain stimulation,” in Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security
2019
Cited alongside, same era.
T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al
2020
Cited alongside, same era.

K. Karra, C. Ashcraft, and N. Fendley, “The trojai software framework: An opensource tool for embedding trojans into deep learning models,” arXiv preprint arXiv:2003.07233
Original
2020
Later among the works it cites.
G. Shen, Y. Liu, G. Tao, S. An, Q. Xu, S. Cheng, S. Ma, and X. Zhang, “Backdoor scanning for deep neural networks through k-arm optimization,” in International Conference on Machine Learning
2021
Later among the works it cites.
X. Zhang, H. Chen, and F. Koushanfar, “Tad: Trigger approximation based black-box trojan detection for ai,” arXiv preprint arXiv:2102.01815
Original
2021
Later among the works it cites.
C. Chen and J. Dai, “Mitigating backdoor attacks in lstm-based text classification systems by backdoor keyword identification,” Neurocomputing
2021
Later among the works it cites.
W. Yang, Y. Lin, P. Li, J. Zhou, and X. Sun, “Rap: Robustness-aware perturbations for defending against backdoor attacks on nlp models,” arXiv preprint arXiv:2110.07831
Original
2021
Later among the works it cites.

alphaXiv searches the wider corpus for related work and actual follow-ups.

alphaXiv is searching for related work…

Reading the bibliography…