Obserwuj
Yingqi Liu
Tytuł
Cytowane przez
Cytowane przez
Rok
Trojaning attack on neural networks
Y Liu, S Ma, Y Aafer, WC Lee, J Zhai, W Wang, X Zhang
25th Annual Network And Distributed System Security Symposium (NDSS 2018), 2018
11902018
Abs: Scanning neural networks for back-doors by artificial brain stimulation
Y Liu, WC Lee, G Tao, S Ma, Y Aafer, X Zhang
Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications …, 2019
4072019
Nic: Detecting adversarial samples with neural network invariant checking
S Ma, Y Liu, G Tao, WC Lee, X Zhang
26th Annual network and distributed system security symposium (NDSS 2019), 2019
2872019
MODE: automated neural network model debugging via state differential analysis and input selection
S Ma, Y Liu, WC Lee, X Zhang, A Grama
Proceedings of the 2018 26th ACM Joint Meeting on European Software …, 2018
1882018
Attacks meet interpretability: Attribute-steered detection of adversarial samples
G Tao, S Ma, Y Liu, X Zhang
Advances in Neural Information Processing Systems 31, 2018
1832018
Composite backdoor attack for deep neural network by mixing existing benign features
J Lin, L Xu, Y Liu, X Zhang
Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications …, 2020
1812020
Deep feature space trojan attack of neural networks by controlled detoxification
S Cheng, Y Liu, S Ma, X Zhang
Proceedings of the AAAI Conference on Artificial Intelligence 35 (2), 1148-1156, 2021
1262021
Backdoor scanning for deep neural networks through k-arm optimization
G Shen, Y Liu, G Tao, S An, Q Xu, S Cheng, S Ma, X Zhang
International Conference on Machine Learning, 9525-9536, 2021
952021
Better trigger inversion optimization in backdoor scanning
G Tao, G Shen, Y Liu, S An, Q Xu, S Ma, P Li, X Zhang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
532022
Piccolo: Exposing complex backdoors in nlp transformer models
Y Liu, G Shen, G Tao, S An, S Ma, X Zhang
2022 IEEE Symposium on Security and Privacy (SP), 2025-2042, 2022
512022
Model orthogonalization: Class distance hardening in neural networks for better security
G Tao, Y Liu, G Shen, Q Xu, S An, Z Zhang, X Zhang
2022 IEEE Symposium on Security and Privacy (SP), 1372-1389, 2022
412022
Complex backdoor detection by symmetric feature differencing
Y Liu, G Shen, G Tao, Z Wang, S Ma, X Zhang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
372022
Black-box adversarial sample generation based on differential evolution
J Lin, L Xu, Y Liu, X Zhang
Journal of Systems and Software 170, 110767, 2020
342020
LAMP: data provenance for graph based machine learning algorithms through derivative computation
S Ma, Y Aafer, Z Xu, WC Lee, J Zhai, Y Liu, X Zhang
Proceedings of the 2017 11th Joint Meeting on Foundations of Software …, 2017
312017
Fault localization for null pointer exception based on stack trace and program slicing
S Jiang, W Li, H Li, Y Zhang, H Zhang, Y Liu
2012 12th International Conference on Quality Software, 9-12, 2012
262012
Constrained optimization with dynamic bound-scaling for effective nlp backdoor defense
G Shen, Y Liu, G Tao, Q Xu, Z Zhang, S An, S Ma, X Zhang
International Conference on Machine Learning, 19879-19892, 2022
252022
Trader: Trace divergence analysis and embedding regulation for debugging recurrent neural networks
G Tao, S Ma, Y Liu, Q Xu, X Zhang
Proceedings of the ACM/IEEE 42nd International Conference on Software …, 2020
132020
White-box program tuning
WC Lee, Y Liu, P Liu, S Ma, H Choi, X Zhang, R Gupta
2019 IEEE/ACM International Symposium on Code Generation and Optimization …, 2019
92019
Mitigating the dependence confounding effect for effective predicate-based statistical fault localization
X Wang, S Jiang, X Ju, H Cao, Y Liu
2015 IEEE 39th Annual Computer Software and Applications Conference 2, 105-114, 2015
52015
Pad: Programming third-party web advertisement censorship
W Wang, Y Kwon, Y Zheng, Y Aafer, IL Kim, WC Lee, Y Liu, W Meng, ...
2017 32nd IEEE/ACM International Conference on Automated Software …, 2017
42017
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20