Zhan Qin

Zhejiang University of Science and Technology — China

Computer Science · Physical Sciences

38h-index6.0kcitations156works5.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Privacy-Preserving Technologies in Data(48), Adversarial Robustness in Machine Learning(28), Advanced Malware Detection Techniques(27), Cryptography and Data Security(19), Mobile Crowdsensing and Crowdsourcing(19)

Publications156 total

Combating Concept Drift with Explanatory Detection and Adaptation for Android Malware Classification
2025· 1 citedOpen Access
Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation
ArXiv.org·2025Open Access
External Data Extraction Attacks against Retrieval-Augmented Large Language Models
arXiv (Cornell University)·2025Open Access
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
arXiv (Cornell University)·2025Open Access
AttMark: Attention Based Model Watermarking Against Stealing Attacks
IEEE Transactions on Dependable and Secure Computing·2025
Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint
ArXiv.org·2025Open Access
Quantifying Conversation Drift in MCP via Latent Polytope
arXiv (Cornell University)·2025Open Access
DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
arXiv (Cornell University)·2025Open Access
Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey
ACM Transactions on Software Engineering and Methodology·2025· 2 cited
DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective
arXiv (Cornell University)·2025Open Access
Artificial intelligence security and privacy: a survey
Science China Information Sciences·2025· 5 citedOpen Access
Rethinking Data Protection in the (Generative) Artificial Intelligence Era
arXiv (Cornell University)·2025Open Access
GFuzz4CAN: A Generative Model-based Fuzzing Method for In-vehicle Controller Area Network
2025
On Benchmarking Code LLMs for Android Malware Analysis
2025· 3 citedOpen Access
DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization
arXiv (Cornell University)·2025Open Access
WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
arXiv (Cornell University)·2025Open Access
Towards Sample-Specific Backdoor Attack With Clean Labels via Attribute Trigger
IEEE Transactions on Dependable and Secure Computing·2025· 1 cited
CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
arXiv (Cornell University)·2025Open Access
Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
arXiv (Cornell University)·2025Open Access
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
arXiv (Cornell University)·2025Open Access
page 1 of 8Next →

Frequent Co-authors

Kui Ren(25), Kui Ren(11), Cong Wang(8), Qian Wang(7), Zhibo Wang(6), Chenglin Miao(4), Lü Su(4), Yaliang Li(4), Zijian Zhang(4), Liehuang Zhu(4), Shengshan Hu(4), Yin Yang(3), Ting Yu(3), Issa Khalil(3), Xiaokui Xiao(3), Chugui Xu(3), Ju Ren(3), Yaoxue Zhang(3), Houping Xiao(3), Haitao Xu(3)