Liming Lu

Liming Lu

Auto-generated profile, based on publicly available information

Liming Lu

School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing, China

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2026 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
SPShuchao Pang
Shuchao Pang
XZXiyu Zeng
Xiyu Zeng
SLSiyuan Liang
Siyuan Liang
LLLiming Lu
Liming Lu
HZHaotian Zhu
Haotian Zhu
JXJason Xue
Jason Xue

5 March 2026 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
LLLiming Lu
Liming Lu
SPShuchao Pang
Shuchao Pang
JWJiakai Wang
Jiakai Wang
XGXiang Gu
Xiang Gu
YLYunhuai Liu
Yunhuai Liu
YZYongbin Zhou
Yongbin Zhou
Quantization-conditioned backdoor attacks, which exploit model quantization states to trigger malicious behavior, pose a hidden threat to deep learning security. However, current studies ignore the feasibility of attacks, i.e., detection visibility, and computational overhead, leading to significant constraints on their practical deployment in real-world adversarial scenarios. To address these limitations, we propose Quantization-conditioned Efficient Stealthy Trojan (QuEST), a novel framework that enhances both the stealth and efficiency of backdoor attacks under quantization constraints. For enhancing stealthiness, we design a stealth-optimized training scheme that benefits from the parametric backdoor injection and trigger scaling augmentation to maintain the consistency of model behavior during attack. In this way, the defender will fail to capture the suspicious behavior differences for detection due to the made efforts in both model-side and data-side. To improve efficiency, we introduce information-guided parameter sharing, which utilizes parameter redundancy analysis and Fisher divergence metrics to identify a minimal amount of quantization-preserved parameters for back-door injection. These parameters are strategically shared between the malicious and benign models, enabling concurrent training and substantially reducing overall training time. Extensive experiments demonstrate that QuEST maintains competitive attack success rates while improving stealth performance by 18.75% and reducing computational costs by 26.66% on average compared to state-of-the-art methods, highlighting QuEST’s potential for more practical adversarial deployments in real-world scenarios. Our code is available here.

9 November 2026
Verified
Conference Paper
Open access
XZXiyu Zeng
Xiyu Zeng
LLLiming Lu
Liming Lu
XZXu Zheng
Xu Zheng
JDJiawei Du
Jiawei Du
FLFanzhen Liu
Fanzhen Liu
YYYazhou Yao
Yazhou Yao

14 November 2026
Verified
Conference Paper
Open access
ELEnguang Liu
Enguang Liu
ZLZhigang Lu
Zhigang Lu
SLSiyuan Liang
Siyuan Liang
LLLiming Lu
Liming Lu
XZXiyu Zeng
Xiyu Zeng
SPShuchao Pang
Shuchao Pang