Invisible backdoor attacks on deep neural networks via steganography and regularization S Li, M Xue, BZH Zhao, H Zhu, X Zhang IEEE Transactions on Dependable and Secure Computing 18 (5), 2088-2105, 2020 | 412 | 2020 |
Hidden backdoors in human-centric language models S Li, H Liu, T Dong, BZH Zhao, M Xue, H Zhu, J Lu Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications …, 2021 | 153 | 2021 |
On the (in) feasibility of attribute inference attacks on machine learning models BZH Zhao, A Agrawal, C Coburn, HJ Asghar, R Bhaskar, MA Kaafar, ... 2021 IEEE European Symposium on Security and Privacy (EuroS&P), 232-251, 2021 | 50 | 2021 |
The audio auditor: user-level membership inference in internet of things voice services Y Miao, M Xue, C Chen, L Pan, J Zhang, BZH Zhao, D Kaafar, Y Xiang arXiv preprint arXiv:1905.07082, 2019 | 40 | 2019 |
A decade of mal-activity reporting: A retrospective analysis of internet malicious activity blacklists BZH Zhao, M Ikram, HJ Asghar, MA Kaafar, A Chaabane, K Thilakarathna Proceedings of the 2019 ACM Asia Conference on Computer and Communications …, 2019 | 38 | 2019 |
Deep learning backdoors S Li, S Ma, M Xue, BZH Zhao Security and Artificial Intelligence: A Crossdisciplinary Approach, 313-334, 2022 | 35 | 2022 |
Not one but many tradeoffs: Privacy vs. utility in differentially private machine learning BZH Zhao, MA Kaafar, N Kourtellis Proceedings of the 2020 ACM SIGSAC Conference on Cloud Computing Security …, 2020 | 29 | 2020 |
On the Resilience of Biometric Authentication Systems against Random Inputs BZH Zhao, HJ Asghar, MA Kaafar Network and Distributed System Security Symposium 2020, 2020 | 27 | 2020 |
Backdoors against natural language processing: A review S Li, T Dong, BZH Zhao, M Xue, S Du, H Zhu IEEE Security & Privacy 20 (5), 50-59, 2022 | 26 | 2022 |
With great dispersion comes greater resilience: Efficient poisoning attacks and defenses for linear regression models J Wen, BZH Zhao, M Xue, A Oprea, H Qian IEEE Transactions on Information Forensics and Security 16, 3709-3723, 2021 | 25 | 2021 |
Touch and you’re trapp (ck) ed: Quantifying the uniqueness of touch gestures for tracking R Masood, BZH Zhao, HJ Asghar, MA Kaafar Proceedings on Privacy Enhancing Technologies, 2018 | 22 | 2018 |
On inferring training data attributes in machine learning models BZH Zhao, HJ Asghar, R Bhaskar, MA Kaafar arXiv preprint arXiv:1908.10558, 2019 | 14 | 2019 |
The audio auditor: Participant-level membership inference in voice-based iot Y Miao, BZH Zhao, M Xue, C Chen, L Pan, J Zhang, D Kaafar, Y Xiang arXiv preprint arXiv:1905.07082, 2019 | 11 | 2019 |
Use of cryptography in malware obfuscation HJ Asghar, BZH Zhao, M Ikram, G Nguyen, D Kaafar, S Lamont, D Coscia Journal of Computer Virology and Hacking Techniques 20 (1), 135-152, 2024 | 10 | 2024 |
DDoD: Dual Denial of Decision Attacks on Human-AI Teams B Tag, N Van Berkel, S Verma, BZH Zhao, S Berkovsky, D Kaafar, ... IEEE Pervasive Computing 22 (1), 77-84, 2023 | 7 | 2023 |
BehavioCog: An observation resistant authentication scheme J Chauhan, BZH Zhao, HJ Asghar, J Chan, MA Kaafar Financial Cryptography and Data Security: 21st International Conference, FC …, 2017 | 7 | 2017 |
Mandera: Malicious node detection in federated learning via ranking W Zhu, BZH Zhao, S Luo, T Liu, K Deng arXiv preprint arXiv:2110.11736, 2021 | 6 | 2021 |
Oriole: Thwarting Privacy Against Trustworthy Deep Learning Models L Chen, H Wang, BZH Zhao, M Xue, H Qian Information Security and Privacy: 26th Australasian Conference, ACISP 2021 …, 2021 | 6 | 2021 |
A longitudinal study of the top 1% toxic Twitter profiles H Qayyum, B Zi Hao Zhao, I Wood, M Ikram, N Kourtellis, M Ali Kaafar Proceedings of the 15th ACM Web Science Conference 2023, 292-303, 2023 | 5 | 2023 |
PALOR: Poisoning attacks against logistic regression J Wen, BZH Zhao, M Xue, H Qian Information Security and Privacy: 25th Australasian Conference, ACISP 2020 …, 2020 | 5 | 2020 |