Login / Signup
Zhangchen Xu
ORCID
Publication Activity (10 Years)
Years Active: 2023-2024
Publications (10 Years): 14
Top Topics
Countermeasures
Autonomous Driving
Evaluation Methods
Safety Critical
Top Venues
CoRR
AsiaCCS
ACL (1)
USENIX Security Symposium
</>
Publications
</>
Fengqing Jiang
,
Zhangchen Xu
,
Luyao Niu
,
Zhen Xiang
,
Bhaskar Ramasubramanian
,
Bo Li
,
Radha Poovendran
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs.
CoRR
(2024)
Yuetai Li
,
Zhangchen Xu
,
Fengqing Jiang
,
Luyao Niu
,
Dinuka Sahabandu
,
Bhaskar Ramasubramanian
,
Radha Poovendran
CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models.
CoRR
(2024)
Zhangchen Xu
,
Fengqing Jiang
,
Luyao Niu
,
Jinyuan Jia
,
Bo Li
,
Radha Poovendran
ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning.
USENIX Security Symposium
(2024)
Fengqing Jiang
,
Zhangchen Xu
,
Luyao Niu
,
Bill Yuchen Lin
,
Radha Poovendran
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates.
CoRR
(2024)
Zhangchen Xu
,
Fengqing Jiang
,
Luyao Niu
,
Jinyuan Jia
,
Radha Poovendran
Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning.
CoRR
(2024)
Zhangchen Xu
,
Fengqing Jiang
,
Luyao Niu
,
Jinyuan Jia
,
Bill Yuchen Lin
,
Radha Poovendran
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding.
ACL (1)
(2024)
Fengqing Jiang
,
Zhangchen Xu
,
Luyao Niu
,
Boxin Wang
,
Jinyuan Jia
,
Bo Li
,
Radha Poovendran
POSTER: Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications.
AsiaCCS
(2024)
Zhangchen Xu
,
Fengqing Jiang
,
Luyao Niu
,
Jinyuan Jia
,
Radha Poovendran
Poster: Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning.
AsiaCCS
(2024)
Zhangchen Xu
,
Fengqing Jiang
,
Luyao Niu
,
Jinyuan Jia
,
Bo Li
,
Radha Poovendran
ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning.
CoRR
(2024)
Zhangchen Xu
,
Fengqing Jiang
,
Luyao Niu
,
Jinyuan Jia
,
Bill Yuchen Lin
,
Radha Poovendran
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding.
CoRR
(2024)
Zhangchen Xu
,
Fengqing Jiang
,
Luyao Niu
,
Yuntian Deng
,
Radha Poovendran
,
Yejin Choi
,
Bill Yuchen Lin
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing.
CoRR
(2024)
Zhangchen Xu
,
Yuetai Li
,
Chenglin Feng
,
Lei Zhang
Exact Fault-Tolerant Consensus with Voting Validity.
IPDPS
(2023)
Fengqing Jiang
,
Zhangchen Xu
,
Luyao Niu
,
Boxin Wang
,
Jinyuan Jia
,
Bo Li
,
Radha Poovendran
Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications.
CoRR
(2023)
Chenglin Feng
,
Zhangchen Xu
,
Xincheng Zhu
,
Paulo Valente Klaine
,
Lei Zhang
Wireless Distributed Consensus in Vehicle to Vehicle Networks for Autonomous Driving.
IEEE Trans. Veh. Technol.
72 (6) (2023)