| SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding Z Xu, F Jiang, L Niu, J Jia, BY Lin, R Poovendran ACL 2024, 2024 | 86 | 2024 |
| ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs F Jiang*, Z Xu*, L Niu*, Z Xiang, B Ramasubramanian, B Li, ... ACL 2024, 2024 | 76 | 2024 |
| Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing Z Xu, F Jiang, L Niu, Y Deng, R Poovendran, Y Choi, BY Lin ICLR 2025, 2024 | 72 | 2024 |
| Wireless Distributed Consensus in Vehicle to Vehicle Networks for Autonomous Driving C Feng, Z Xu, X Zhu, PV Klaine, L Zhang IEEE Transactions on Vehicular Technology, 2023 | 32 | 2023 |
| CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models Y Li*, Z Xu*, F Jiang, L Niu, D Sahabandu, B Ramasubramanian, ... EMNLP 2024, 2024 | 7 | 2024 |
| Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications F Jiang, Z Xu, L Niu, B Wang, J Jia, B Li, R Poovendran Instruction Workshop @ NeurIPS 2023, 2023 | 5* | 2023 |
| Exact Fault-Tolerant Consensus With Voting Validity Z Xu, Y Li, C Feng, L Zhang IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2023 | 4 | 2023 |
| Stronger Models are NOT Stronger Teachers for Instruction Tuning Z Xu, F Jiang, L Niu, BY Lin, R Poovendran NAACL 2025, 2024 | 3 | 2024 |
| ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates F Jiang*, Z Xu*, L Niu, BY Lin, R Poovendran AAAI 2025, 2024 | 2 | 2024 |
| ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning Z Xu, F Jiang, L Niu, J Jia, B Li, R Poovendran Usenix Security 2024, 2024 | 1 | 2024 |
| Distributed Consensus Network: A Modularized Communication Framework and Reliability Probabilistic Analysis Y Li, Z Xu, Y Wang, Z Zhou, L Zhang, J Crowcroft arXiv preprint arXiv:2502.12069, 2025 | | 2025 |
| Small Models Struggle to Learn from Strong Reasoners Y Li, X Yue, Z Xu, F Jiang, L Niu, BY Lin, B Ramasubramanian, ... arXiv preprint arXiv:2502.12143, 2025 | | 2025 |
| SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities F Jiang, Z Xu, Y Li, L Niu, Z Xiang, B Li, BY Lin, R Poovendran arXiv preprint arXiv:2502.12025, 2025 | | 2025 |
| Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning Z Xu*, F Jiang*, L Niu, J Jia, R Poovendran The 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI), 2024 | | 2024 |
Radha PoovendranProfessor of ECE, University of WashingtonVahvistettu sähköpostiosoite verkkotunnuksessa uw.edu