| Topology attack and defense for graph neural networks: An optimization perspective K Xu, H Chen, S Liu, PY Chen, TW Weng, M Hong, X Lin IJCAI 2019, 2019 | 579 | 2019 |
| Autozoom: Autoencoder-based zeroth order optimization method for attacking black-box neural networks CC Tu, P Ting, PY Chen, S Liu, H Zhang, J Yi, CJ Hsieh, SM Cheng Proceedings of the AAAI conference on artificial intelligence 33 (01), 742-749, 2019 | 535 | 2019 |
| Adversarial t-shirt! evading person detectors in a physical world K Xu, G Zhang, S Liu, Q Fan, M Sun, H Chen, PY Chen, Y Wang, X Lin ECCV 2020, 665-681, 2020 | 524 | 2020 |
| The lottery ticket hypothesis for pre-trained bert networks T Chen, J Frankle, S Chang, S Liu, Y Zhang, Z Wang, M Carbin Advances in neural information processing systems 33, 15834-15846, 2020 | 481 | 2020 |
| On the convergence of a class of adam-type algorithms for non-convex optimization X Chen, S Liu, R Sun, M Hong ICLR 2019, 2018 | 446 | 2018 |
| A primer on zeroth-order optimization in signal processing and machine learning: Principals, recent advances, and applications S Liu, PY Chen, B Kailkhura, G Zhang, AO Hero III, PK Varshney IEEE Signal Processing Magazine 37 (5), 43-54, 2020 | 372 | 2020 |
| Sign-opt: A query-efficient hard-label adversarial attack M Cheng, S Singh, P Chen, PY Chen, S Liu, CJ Hsieh ICLR 2020, 2019 | 342 | 2019 |
| Adversarial robustness: From self-supervised pre-training to fine-tuning T Chen, S Liu, S Chang, Y Cheng, L Amini, Z Wang CVPR, 699-708, 2020 | 333 | 2020 |
| Rethinking machine unlearning for large language models S Liu, Y Yao, J Jia, S Casper, N Baracaldo, P Hase, Y Yao, CY Liu, X Xu, ... Nature Machine Intelligence, 1-14, 2025 | 329 | 2025 |
| Salun: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation C Fan, J Liu, Y Zhang, D Wei, E Wong, S Liu ICLR 2024 (Spotlight), 2023 | 290 | 2023 |
| Robust overfitting may be mitigated by properly learned smoothening T Chen, Z Zhang, S Liu, S Chang, Z Wang International conference on learning representations, 2020 | 259 | 2020 |
| Zeroth-order stochastic variance reduction for nonconvex optimization S Liu, B Kailkhura, PY Chen, P Ting, S Chang, L Amini Advances in neural information processing systems 31, 2018 | 255 | 2018 |
| Model Sparsity Can Simplify Machine Unlearning J Jia, J Liu, P Ram, Y Yao, G Liu, Y Liu, P Sharma, S Liu NeurIPS 2023 (Spotlight), 2023 | 241* | 2023 |
| Sensor selection for estimation with correlated measurement noise S Liu, SP Chepuri, M Fardad, E Maşazade, G Leus, PK Varshney IEEE Transactions on Signal Processing 64 (13), 3509-3522, 2016 | 241 | 2016 |
| Adversarial robustness vs. model compression, or both? S Ye, K Xu, S Liu, H Cheng, JH Lambrechts, H Zhang, A Zhou, K Ma, ... Proceedings of the IEEE/CVF international conference on computer vision, 111-120, 2019 | 233 | 2019 |
| Is there a trade-off between fairness and accuracy? a perspective using mismatched hypothesis testing S Dutta, D Wei, H Yueksel, PY Chen, S Liu, K Varshney International conference on machine learning, 2803-2813, 2020 | 231 | 2020 |
| Cnn-cert: An efficient framework for certifying robustness of convolutional neural networks A Boopathy, TW Weng, PY Chen, S Liu, L Daniel Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 3240-3247, 2019 | 210 | 2019 |
| Structured adversarial attack: Towards general implementation and better interpretability K Xu, S Liu, P Zhao, PY Chen, H Zhang, Q Fan, D Erdogmus, Y Wang, ... ICLR 2019, 2018 | 202 | 2018 |
| Practical detection of trojan neural networks: Data-limited and data-free cases R Wang, G Zhang, S Liu, PY Chen, J Xiong, M Wang European Conference on Computer Vision, 222-238, 2020 | 197 | 2020 |
| To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images... for now Y Zhang, J Jia, X Chen, A Chen, Y Zhang, J Liu, K Ding, S Liu European Conference on Computer Vision, 385-403, 2024 | 188 | 2024 |
Pin-Yu ChenPrincipal Research Scientist, IBM Research AI; MIT-IBM Watson AI Lab; RPI-IBM AIRCVerified email at ibm.com
