Scholar
Songlei Jian
Google Scholar ID: 5O6bAuwAAAAJ
NUDT
representation learning
machine learning
data science
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,141
H-index
19
i10-index
27
Publications
20
Co-authors
4
list available
Contact
Email
jiansonglei@nudt.edu.cn
GitHub
Open ↗
Publications
4 items
BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator
2026
Cited
0
Cognitive Chunking for Soft Prompts: Accelerating Compressor Learning via Block-wise Causal Masking
2026
Cited
0
JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
arXiv.org · 2026
Cited
0
Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience
2025
Cited
0
Resume (English only)
Academic Achievements
Published over 30 high-quality papers in premier venues including AAAI, ICML, The ACM Web Conference, IJCAI, CIKM, IEEE TKDE, and Computer & Security
Served as PC member for more than 10 top international conferences such as AAAI and IJCAI
Reviewer for over 10 prestigious journals including IEEE TPAMI, IEEE TKDE, IEEE TNNLS, and IPM
Paper on jailbreak attack accepted by EMNLP 2025
Paper on few-shot anomaly detection accepted by CIKM 2025
Paper on backdoor defense accepted by ACL 2025
Multiple papers published on CNN inference optimization and memory management on CPUs
Paper on unsupervised time series anomaly detection accepted by TKDE, with source code released
Paper accepted by ICASSP 2024 selected as Best Student Paper
Papers on multimodal fake news detection and semi-supervised anomaly detection accepted by Information Processing & Management
Paper on log anomaly detection accepted by ISSRE 2023
Paper on unsupervised anomaly detection accepted by ICML 2023
Paper on multimodal fake news detection accepted by ICASSP 2023
Papers on unsupervised network intrusion detection and representation learning-based intrusion detection system accepted by Computer & Security
Paper on graph pooling accepted by CIKM 2022
Papers on graph representation and categorical data representation accepted by TKDE
Paper on representation learning for heterogeneous domains accepted by AAAI 2020
Two papers on network representation and recommender systems accepted by AAAI 2019
Paper on few-shot learning accepted by CVPR 2021
Paper on outlier interpretation accepted by WWW 2021
Presented tutorial at PAKDD 2018 in Melbourne, Australia
Co-authors
4 total
Longbing Cao
Distinguished Chair Professor in AI & ARC Future Fellow (Level 3), Macquarie University
Liang Hu
Tongji University
Guansong Pang
Assistant Professor of Computer Science, Singapore Management University
Xinwang Liu
Senior Member of IEEE and CCF, NUDT
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up