Chengkun Wei

Orcid: 0000-0001-8849-8808

According to our database1, Chengkun Wei authored at least 29 papers between 2020 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
EditCoT: A Stepwise Chain-of-Thought Reasoning Framework for Multi-Intent Text Revision.
ACM Trans. Asian Low Resour. Lang. Inf. Process., March, 2026

Distributed Rate Limiting Under Decentralized Cloud Networks.
IEEE Trans. Mob. Comput., February, 2026

Watermarking LLM Agent Trajectories.
CoRR, February, 2026

MirrorFuzz: Leveraging LLM and Shared Bugs for Deep Learning Framework APIs Fuzzing.
IEEE Trans. Software Eng., January, 2026

Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models.
CoRR, January, 2026

Dialogue Injection Attack: Jailbreaking LLMs Through Context Manipulation.
IEEE Trans. Inf. Forensics Secur., 2026

Enhancing Meme Emotion Understanding with Multi-Level Modality Enhancement and Dual-Stage Modal Fusion.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
DC-SGD: Differentially Private SGD With Dynamic Clipping Through Gradient Norm Distribution Estimation.
IEEE Trans. Inf. Forensics Secur., 2025

I Know Who Clones Your Code: Interpretable Smart Contract Similarity Detection.
IEEE Trans. Dependable Secur. Comput., 2025

GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors.
Proceedings of the 34th USENIX Security Symposium, 2025

NVMePass: A Lightweight, High-performance and Scalable NVMe Virtualization Architecture with I/O Queues Passthrough.
Proceedings of the IEEE International Symposium on High Performance Computer Architecture, 2025

R.R.: Unveiling LLM Training Privacy through Recollection and Ranking.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
HydraRPC: RPC in the CXL Era.
Proceedings of the 2024 USENIX Annual Technical Conference, 2024

Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud.
Proceedings of the ACM SIGCOMM 2024 Conference, 2024

LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors.
Proceedings of the 31st Annual Network and Distributed System Security Symposium, 2024

CMDRL: A Markovian Distributed Rate Limiting Algorithm in Cloud Networks.
Proceedings of the 8th Asia-Pacific Workshop on Networking, 2024

2023
EduNER: a Chinese named entity recognition dataset for education research.
Neural Comput. Appl., August, 2023

cuZK: Accelerating Zero-Knowledge Proof with A Faster Parallel Multi-Scalar Multiplication Algorithm on GPUs.
IACR Trans. Cryptogr. Hardw. Embed. Syst., 2023

High-performance and Scalable Software-based NVMe Virtualization Mechanism with I/O Queues Passthrough.
CoRR, 2023

Achelous: Enabling Programmability, Elasticity, and Reliability in Hyperscale Cloud Networks.
Proceedings of the ACM SIGCOMM 2023 Conference, 2023

Poster: Triton: Accelerating vSwitch with Flexibility through Hardware Assisting not Bypassing Software.
Proceedings of the ACM SIGCOMM 2023 Conference, 2023

BM-Store: A Transparent and High-performance Local Storage Architecture for Bare-metal Clouds Enabling Large-scale Deployment.
Proceedings of the IEEE International Symposium on High-Performance Computer Architecture, 2023

DPMLBench: Holistic Evaluation of Differentially Private Machine Learning.
Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023

Securely Sampling Discrete Gaussian Noise for Multi-Party Differential Privacy.
Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023

HyQ: Hybrid I/O Queue Architecture for NVMe over Fabrics to Enable High- Performance Hardware Offloading.
Proceedings of the 23rd IEEE/ACM International Symposium on Cluster, 2023

2022
cuZK: Accelerating Zero-Knowledge Proof with A Faster Parallel Multi-Scalar Multiplication Algorithm on GPUs.
IACR Cryptol. ePrint Arch., 2022

2021
OB-WSPES: A Uniform Evaluation System for Obfuscation-Based Web Search Privacy.
IEEE Trans. Dependable Secur. Comput., 2021

2020
AsgLDP: Collecting and Generating Decentralized Attributed Graphs With Local Differential Privacy.
IEEE Trans. Inf. Forensics Secur., 2020


  Loading...