| Poisonedrag: Knowledge corruption attacks to retrieval-augmented generation of large language models W Zou, R Geng, B Wang, J Jia USENIX Security Symposium, 2024 | 80* | 2024 |
| Provably robust multi-bit watermarking for ai-generated text via error correction code W Qu, D Yin, Z He, W Zou, T Tao, J Jia, J Zhang arXiv preprint arXiv:2401.16820, 2024 | 8 | 2024 |
| Analyzing robustness of end-to-end neural models for automatic speech recognition G Rajendran, W Zou arXiv preprint arXiv:2208.08509, 2022 | 5 | 2022 |
| MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models Y Wang, H Fu, W Zou, J Jia IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 | 2 | 2024 |
| FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models Y Wang, W Zou, J Jia IEEE Symposium on Security and Privacy (IEEE S&P), 2024 | | 2024 |
Jinyuan JiaAssistant Professor, Penn StateVerified email at psu.edu