Li Shen

Li Shen

Auto-generated profile, based on publicly available information

Li Shen

School of Professional Studies, New York University, New York, United States

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
18 August 2025 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
KCKang Chen
Kang Chen
XZXiuze Zhou
Xiuze Zhou
YLYuanguo Lin
Yuanguo Lin
SFShibo Feng
Shibo Feng
LSLi Shen
Li Shen
PWPengcheng Wu
Pengcheng Wu
Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. First, we analyze privacy leakage and attacks in LLMs, focusing on how these models unintentionally expose sensitive information through techniques such as model inversion, training data extraction, and membership inference. We investigate the mechanisms of privacy leakage, including the unauthorized extraction of training data and the potential exploitation of these vulnerabilities by malicious actors. Next, we review existing privacy protection against such risks, such as inference detection, federated learning, backdoor mitigation, and confidential computing, and assess their effectiveness in preventing privacy leakage. Furthermore, we highlight key practical challenges and propose future research directions to develop secure and privacy-preserving LLMs, emphasizing privacy risk assessment, secure knowledge transfer between models, practical deployment and trade-offs, and interdisciplinary frameworks for privacy governance. Ultimately, this survey aims to establish a roadmap for addressing escalating privacy challenges in the LLMs domain.

4 May 2025 in arXiv
Verified
Preprint
Open access
PDF file
KCKang Chen
Kang Chen
XZXiuze Zhou
Xiuze Zhou
YLYuanguo Lin
Yuanguo Lin
SFShibo Feng
Shibo Feng
LSLi Shen
Li Shen
PWPengcheng Wu
Pengcheng Wu
Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. First, we analyze privacy leakage and attacks in LLMs, focusing on how these models unintentionally expose sensitive information through techniques such as model inversion, training data extraction, and membership inference. We investigate the mechanisms of privacy leakage, including the unauthorized extraction of training data and the potential exploitation of these vulnerabilities by malicious actors. Next, we review existing privacy protection against such risks, such as inference detection, federated learning, backdoor mitigation, and confidential computing, and assess their effectiveness in preventing privacy leakage. Furthermore, we highlight key practical challenges and propose future research directions to develop secure and privacy-preserving LLMs, emphasizing privacy risk assessment, secure knowledge transfer between models, and interdisciplinary frameworks for privacy governance. Ultimately, this survey aims to establish a roadmap for addressing escalating privacy challenges in the LLMs domain.

4 August 2025 in arXiv
Verified
Preprint
Open access
PDF file
KCKang Chen
Kang Chen
XZXiuze Zhou
Xiuze Zhou
YLYuanguo Lin
Yuanguo Lin
JSJinhe Su
Jinhe Su
YYYuanhui Yu
Yuanhui Yu
FLFan Lin
Fan Lin
Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often collected from diverse and uncurated sources, which exposes them to serious data security risks. Harmful or malicious data can compromise model behavior, leading to issues such as toxic output, hallucinations, and vulnerabilities to threats such as prompt injection or data poisoning. As LLMs continue to be integrated into critical real-world systems, understanding and addressing these data-centric security risks is imperative to safeguard user trust and system reliability. This survey offers a comprehensive overview of the main data security risks facing LLMs and reviews current defense strategies, including adversarial training, RLHF, and data augmentation. Additionally, we categorize and analyze relevant datasets used for assessing robustness and security across different domains, providing guidance for future research. Finally, we highlight key research directions that focus on secure model updates, explainability-driven defenses, and effective governance frameworks, aiming to promote the safe and responsible development of LLM technology. This work aims to inform researchers, practitioners, and policymakers, driving progress toward data security in LLMs.

25 August 2026 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
KCKang Chen
Kang Chen
XZXiuze Zhou
Xiuze Zhou
YYYuanhui Yu
Yuanhui Yu
YLYuanguo Lin
Yuanguo Lin
HCHefeng Chen
Hefeng Chen
LSLi Shen
Li Shen
Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often collected from diverse and uncurated sources, which exposes them to serious data security risks. Harmful or malicious data can compromise model behavior, leading to toxic outputs or hallucinations, while also creating vulnerabilities to data-driven attacks such as prompt injection and data poisoning. As LLMs continue to be integrated into critical real-world systems, understanding and addressing these data-centric security risks is imperative to safeguard user trust and system reliability. This survey offers a comprehensive overview of the main data security risks facing LLMs and reviews current defense strategies, including adversarial training, data cleaning, output guardrails, Reinforcement Learning from Human Feedback (RLHF), data augmentation, and Retrieval-Augmented Generation (RAG)/agent defenses. Additionally, we categorize and analyze relevant datasets used for assessing robustness and security across different domains, providing guidance for future research. Finally, we highlight key research directions that focus on data provenance and traceability, verifiable machine forgetting, secure model updates, standardized evaluation framework, explainability-driven security analysis, and effective governance frameworks, aiming to promote the safe and responsible development of LLM technology. This work seeks to inform researchers, practitioners, and policymakers, driving progress toward data security in LLMs.