Luyao Niu

Publication Activity (10 Years)

Years Active: 2016-2024
Publications (10 Years): 81

Top Topics

Partially Observable Environments

Safety Analysis

Public Transportation

Top Venues

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)
Hongchao Zhang, Luyao Niu, Andrew Clark, Radha Poovendran
Fault Tolerant Neural Control Barrier Functions for Robotic Systems under Sensor Faults and Attacks. ICRA (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)
He Zhu, Wenjia Zhang, Nuoxian Huang, Boyang Li, Luyao Niu, Zipei Fan, Tianle Lun, Yicheng Tao, Junyou Su, Zhaoya Gong, Chenyu Fang, Xing Liu
PlanGPT: Enhancing Urban Planning with Tailored Language Model and Efficient Retrieval. CoRR (2024)
Hongchao Zhang, Luyao Niu, Andrew Clark, Radha Poovendran
Fault Tolerant Neural Control Barrier Functions for Robotic Systems under Sensor Faults and Attacks. 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)
Dinuka Sahabandu, Xiaojun Xu, Arezoo Rajabi, Luyao Niu, Bhaskar Ramasubramanian, Bo Li, Radha Poovendran
POSTER: Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors. AsiaCCS (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)
Dinuka Sahabandu, Xiaojun Xu, Arezoo Rajabi, Luyao Niu, Bhaskar Ramasubramanian, Bo Li, Radha Poovendran
Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors. CoRR (2024)
Zhouchi Li, Luyao Niu, Andrew Clark
LQG Reference Tracking With Safety and Reachability Guarantees Under Unknown False Data Injection Attacks. IEEE Trans. Autom. Control. 68 (2) (2023)
Abdullah Al Maruf, Luyao Niu, Bhaskar Ramasubramanian, Andrew Clark, Radha Poovendran
Cognitive Bias-Aware Dissemination Strategies for Opinion Dynamics with External Information Sources. AAMAS (2023)
Arezoo Rajabi, Surudhi Asokraj, Fengqing Jiang, Luyao Niu, Bhaskar Ramasubramanian, James A. Ritcey, Radha Poovendran
MDTD: A Multi Domain Trojan Detector for Deep Neural Networks. CoRR (2023)
Luyao Niu, Bhaskar Ramasubramanian, Andrew Clark, Radha Poovendran
Robust Satisfaction of Metric Interval Temporal Logic Objectives in Adversarial Environments. Games 14 (2) (2023)
Luyao Niu, Andrew Clark, Radha Poovendran
Necessary and Sufficient Conditions for Satisfying Linear Temporal Logic Constraints Using Control Barrier Certificates. CDC (2023)
Luyao Niu, Abdullah Al Maruf, Andrew Clark, J. Sukarno Mertoguno, Radha Poovendran
A Compositional Resilience Index for Computationally Efficient Safety Analysis of Interconnected Systems. CoRR (2023)
Luyao Niu, Abdullah Al Maruf, Andrew Clark, J. Sukarno Mertoguno, Radha Poovendran
A Compositional Resilience Index for Computationally Efficient Safety Analysis of Interconnected Systems. CDC (2023)
Jinyuan Jia, Zhuowen Yuan, Dinuka Sahabandu, Luyao Niu, Arezoo Rajabi, Bhaskar Ramasubramanian, Bo Li, Radha Poovendran
FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning. NeurIPS (2023)
Arezoo Rajabi, Surudhi Asokraj, Fengqing Jiang, Luyao Niu, Bhaskar Ramasubramanian, James A. Ritcey, Radha Poovendran
MDTD: A Multi-Domain Trojan Detector for Deep Neural Networks. CCS (2023)
Abdullah Al Maruf, Luyao Niu, Bhaskar Ramasubramanian, Andrew Clark, Radha Poovendran
Risk-Aware Distributed Multi-Agent Reinforcement Learning. CoRR (2023)
Arezoo Rajabi, Dinuka Sahabandu, Luyao Niu, Bhaskar Ramasubramanian, Radha Poovendran
LDL: A Defense for Label-Based Membership Inference Attacks. AsiaCCS (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)
Shiyu Cheng, Luyao Niu, Andrew Clark, Radha Poovendran
A Submodular Energy Function Approach to Controlled Islanding with Provable Stability. CDC (2023)
Luyao Niu, Abdullah Al Maruf, Andrew Clark, J. Sukarno Mertoguno, Radha Poovendran
POSTER: A Common Framework for Resilient and Safe Cyber-Physical System Design. AsiaCCS (2023)
Luyao Niu, Dinuka Sahabandu, Andrew Clark, Radha Poovendran
A Hybrid Submodular Optimization Approach to Controlled Islanding with Post-Disturbance Stability Guarantees. CoRR (2023)
Abdullah Al Maruf, Luyao Niu, Bhaskar Ramasubramanian, Andrew Clark, Radha Poovendran
Learning Dissemination Strategies for External Sources in Opinion Dynamic Models with Cognitive Biases. IJCAI (2023)
Abdullah Al Maruf, Luyao Niu, Andrew Clark, J. Sukarno Mertoguno, Radha Poovendran
A Timing-Based Framework for Designing Resilient Cyber-Physical Systems under Safety Constraint. ACM Trans. Cyber Phys. Syst. 7 (3) (2023)
Luyao Niu, Abdullah Al Maruf, Andrew Clark, J. Sukarno Mertoguno, Radha Poovendran
An Analytical Framework for Control Synthesis of Cyber-Physical Systems with Safety Guarantee. CDC (2022)
Dinuka Sahabandu, Arezoo Rajabi, Luyao Niu, Bo Li, Bhaskar Ramasubramanian, Radha Poovendran
Game of Trojans: A Submodular Byzantine Approach. CoRR (2022)
Hongchao Zhang, Shiyu Cheng, Luyao Niu, Andrew Clark
Barrier Certificate based Safe Control for LiDAR-based Systems under Sensor Faults and Attacks. CoRR (2022)
Dinuka Sahabandu, Luyao Niu, Andrew Clark, Radha Poovendran
A Hybrid Submodular Optimization Approach to Controlled Islanding with Heterogeneous Loads. SmartGridComm (2022)
Luyao Niu, Abdullah Al Maruf, Andrew Clark, J. Sukarno Mertoguno, Radha Poovendran
An Analytical Framework for Control Synthesis of Cyber-Physical Systems with Safety Guarantee. CoRR (2022)
Luyao Niu, Zhouchi Li, Andrew Clark
Abstraction-Free Control Synthesis to Satisfy Temporal Logic Constraints under Sensor Faults and Attacks. CDC (2022)
Hongchao Zhang, Shiyu Cheng, Luyao Niu, Andrew Clark
Barrier Certificate based Safe Control for LiDAR-based Systems under Sensor Faults and Attacks. CDC (2022)
Luyao Niu, Dinuka Sahabandu, Andrew Clark, Radha Poovendran
Verifying Safety for Resilient Cyber-Physical Systems via Reactive Software Restart. ICCPS (2022)
Dinuka Sahabandu, Luyao Niu, Andrew Clark, Radha Poovendran
A Submodular Optimization Approach to Stable and Minimally Disruptive Controlled Islanding in Power Systems. ACC (2022)
Abdullah Al Maruf, Luyao Niu, Andrew Clark, J. Sukarno Mertoguno, Radha Poovendran
A Timing-Based Framework for Designing Resilient Cyber-Physical Systems under Safety Constraint. CoRR (2022)
Abdullah Al Maruf, Luyao Niu, Andrew Clark, J. Sukarno Mertoguno, Radha Poovendran
A Compositional Approach to Safety-Critical Resilient Control for Systems with Coupled Dynamics. CoRR (2022)
Luyao Niu, Zhouchi Li, Andrew Clark
Abstraction-Free Control Synthesis to Satisfy Temporal Logic Constraints under Sensor Faults and Attacks. CoRR (2022)
Abdullah Al Maruf, Luyao Niu, Andrew Clark, J. Sukarno Mertoguno, Radha Poovendran
A Compositional Approach to Safety-Critical Resilient Control for Systems with Coupled Dynamics. CDC (2022)
Arezoo Rajabi, Dinuka Sahabandu, Luyao Niu, Bhaskar Ramasubramanian, Radha Poovendran
LDL: A Defense for Label-Based Membership Inference Attacks. CoRR (2022)
Dinuka Sahabandu, Luyao Niu, Andrew Clark, Radha Poovendran
Scalable Planning in Multi-Agent MDPs. CoRR (2021)
Dinuka Sahabandu, Luyao Niu, Andrew Clark, Radha Poovendran
Scalable Planning in Multi-Agent MDPs. CDC (2021)
Luyao Niu, Hongchao Zhang, Andrew Clark
Safety-Critical Control Synthesis for Unknown Sampled-Data Systems via Control Barrier Functions. CoRR (2021)
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark, Linda Bushnell, Radha Poovendran
Secure Control in Partially Observable Environments to Satisfy LTL Specifications. IEEE Trans. Autom. Control. 66 (12) (2021)
Zhouchi Li, Luyao Niu, Andrew Clark
LQG Reference Tracking with Safety and Reachability Guarantees under Unknown False Data Injection Attacks. CoRR (2021)
Luyao Niu, Dinuka Sahabandu, Andrew Clark, Radha Poovendran
A Game-Theoretic Framework for Controlled Islanding in the Presence of Adversaries. CoRR (2021)
Luyao Niu, Andrew Clark
A Differentially Private Incentive Design for Traffic Offload to Public Transportation. ACM Trans. Cyber Phys. Syst. 5 (2) (2021)
Luyao Niu, Dinuka Sahabandu, Andrew Clark, Radha Poovendran
A Game-Theoretic Framework for Controlled Islanding in the Presence of Adversaries. GameSec (2021)
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark, Radha Poovendran
Reinforcement Learning Beyond Expectation. CDC (2021)
Luyao Niu, Jie Fu, Andrew Clark
Optimal Minimum Violation Control Synthesis of Cyber-Physical Systems Under Attacks. IEEE Trans. Autom. Control. 66 (3) (2021)
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark, Radha Poovendran
Reinforcement Learning Beyond Expectation. CoRR (2021)
Luyao Niu, Hongchao Zhang, Andrew Clark
Safety-Critical Control Synthesis for Unknown Sampled-Data Systems via Control Barrier Functions. CDC (2021)
Luyao Niu, Bhaskar Ramasubramanian, Andrew Clark, Linda Bushnell, Radha Poovendran
Control Synthesis for Cyber-Physical Systems to Satisfy Metric Interval Temporal Logic Objectives under Timing and Actuator Attacks. CoRR (2020)
Luyao Niu, Andrew Clark
Control Barrier Functions for Abstraction-Free Control Synthesis under Temporal Logic Constraints. CoRR (2020)
Luyao Niu, Andrew Clark
Control Barrier Functions for Abstraction-Free Control Synthesis under Temporal Logic Constraints. CDC (2020)
Luyao Niu, Bhaskar Ramasubramanian, Andrew Clark, Linda Bushnell, Radha Poovendran
Control Synthesis for Cyber-Physical Systems to Satisfy Metric Interval Temporal Logic Objectives under Timing and Actuator Attacks. ICCPS (2020)
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark, Linda Bushnell, Radha Poovendran
Privacy-Preserving Resilience of Cyber-Physical Systems to Adversaries. CoRR (2020)
Luyao Niu, Andrew Clark
Optimal Secure Control With Linear Temporal Logic Constraints. IEEE Trans. Autom. Control. 65 (6) (2020)
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark, Linda Bushnell, Radha Poovendran
Privacy-Preserving Resilience of Cyber-Physical Systems to Adversaries. CDC (2020)
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark, Linda Bushnell, Radha Poovendran
Secure Control in Partially Observable Environments to Satisfy LTL Specifications. CoRR (2020)
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark, Linda Bushnell, Radha Poovendran
Linear Temporal Logic Satisfaction in Adversarial Environments Using Secure Control Barrier Certificates. GameSec (2019)
Luyao Niu, Andrew Clark
A Framework for Joint Attack Detection and Control Under False Data Injection. GameSec (2019)
Luyao Niu, Andrew Clark
Optimal Secure Control with Linear Temporal Logic Constraints. CoRR (2019)
Luyao Niu, Andrew Clark
A Differentially Private Incentive Design for Traffic Offload to Public Transportation. CoRR (2019)
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark, Linda Bushnell, Radha Poovendran
Linear Temporal Logic Satisfaction in Adversarial Environments using Secure Control Barrier Certificates. CoRR (2019)
Luyao Niu, Zhouchi Li, Andrew Clark
LQG Reference Tracking with Safety and Reachability Guarantees under False Data Injection Attacks. ACC (2019)
Luyao Niu, Andrew Clark
Secure Control Under Linear Temporal Logic Constraints. ACC (2018)
Andrew Clark, Luyao Niu
Linear Quadratic Gaussian Control Under False Data Injection Attacks. ACC (2018)
Luyao Niu, Jie Fu, Andrew Clark
Minimum Violation Control Synthesis on Cyber-Physical Systems under Attacks. CDC (2018)
Luyao Niu, Jie Fu, Andrew Clark
Minimum Violation Control Synthesis on Cyber-Physical Systems under Attacks. CoRR (2018)
Luyao Niu, Andrew Clark
A Differentially Private and Truthful Incentive Mechanism for Traffic Offload to Public Transportation. GameSec (2018)
Luyao Niu, Yingyue Fan, Kaveh Pahlavan, Guanxiong Liu, Yishuang Geng
On the accuracy of Wi-Fi localization using robot and human collected signatures. ICCE (2016)
Luyao Niu, Yuanxiong Guo, Hongning Li, Miao Pan
A Nash Bargaining Approach to Emergency Demand Response in Colocation Data Centers. GLOBECOM (2016)
Luyao Niu, Yuanxiong Guo
Enabling reliable data center demand response via aggregation. e-Energy (2016)