Stebėti
Zhouxing Shi
Pavadinimas
Cituota
Cituota
Metai
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
K Xu*, Z Shi*, H Zhang*, Y Wang, KW Chang, M Huang, B Kailkhura, ...
Advances in Neural Information Processing Systems (*equal contribution), 2020
3062020
On the Adversarial Robustness of Vision Transformers
R Shao, Z Shi, J Yi, PY Chen, CJ Hsieh
TMLR, 2022
2372022
Robustness Verification for Transformers
Z Shi, H Zhang, KW Chang, M Huang, CJ Hsieh
International Conference on Learning Representations, 2020
1362020
A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues
Z Shi, M Huang
Proceedings of the AAAI Conference on Artificial Intelligence, 2019
1062019
Fast Certified Robust Training with Short Warmup
Z Shi*, Y Wang*, H Zhang, J Yi, CJ Hsieh
Advances in Neural Information Processing Systems (*equal contribution), 2021
782021
Red teaming language model detectors with language models
Z Shi*, Y Wang*, F Yin*, X Chen, KW Chang, CJ Hsieh
Transactions of the Association for Computational Linguistics (*equal …, 2024
722024
On the Sensitivity and Stability of Model Interpretations in NLP
F Yin, Z Shi, CJ Hsieh, KW Chang
Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022
43*2022
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation
Z Shi, Y Wang, H Zhang, Z Kolter, CJ Hsieh
Advances in Neural Information Processing Systems, 2022
412022
Neural Network Verification with Branch-and-Bound for General Nonlinearities
Z Shi*, Q Jin*, Z Kolter, S Jana, CJ Hsieh, H Zhang
arXiv preprint arXiv:2405.21063 (*equal contribution), 2024
29*2024
Defending LLMs against Jailbreaking Attacks via Backtranslation
Y Wang*, Z Shi*, A Bai, CJ Hsieh
arXiv preprint arXiv:2402.16459 (*equal contribution), 2024
272024
Robust text captchas using adversarial examples
R Shao, Z Shi, J Yi, PY Chen, CJ Hsieh
2022 IEEE International Conference on Big Data (Big Data), 1495-1504, 2022
222022
Robustness to Modification with Shared Words in Paraphrase Identification
Z Shi, M Huang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language …, 2020
212020
Knowledge-Aided Open-Domain Question Answering
M Zhou, Z Shi, M Huang, X Zhu
arXiv preprint arXiv:2006.05244, 2020
182020
Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation
L Yang, H Dai, Z Shi, CJ Hsieh, R Tedrake, H Zhang
Forty-first International Conference on Machine Learning, 2024
15*2024
Towards robustness certification against universal perturbations
Y Zeng*, Z Shi*, M Jin, F Kang, L Lyu, CJ Hsieh, R Jia
International Conference on Learning Representation (*equal contribution), 2023
132023
Effective robustness against natural distribution shifts for models with different training data
Z Shi, N Carlini, A Balashankar, L Schmidt, CJ Hsieh, A Beutel, Y Qin
Advances in Neural Information Processing Systems 36, 73543-73558, 2023
112023
On the Convergence of Certified Robust Training with Interval Bound Propagation
Y Wang*, Z Shi*, Q Gu, CJ Hsieh
International Conference on Learning Representations (*equal contribution), 2022
92022
Improving the Generation Quality of Watermarked Large Language Models via Word Importance Scoring
Y Li, Y Wang, Z Shi, CJ Hsieh
arXiv preprint arXiv:2311.09668, 2023
62023
Testing Neural Network Verifiers: A Soundness Benchmark with Hidden Counterexamples
X Zhou, H Xu, A Xu, Z Shi, CJ Hsieh, H Zhang
arXiv preprint arXiv:2412.03154, 2024
12024
Certified Training with Branch-and-Bound: A Case Study on Lyapunov-stable Neural Control
Z Shi, CJ Hsieh, H Zhang
arXiv preprint arXiv:2411.18235, 2024
12024
Sistema negali atlikti operacijos. Bandykite vėliau dar kartą.
Straipsniai 1–20