[HTML][HTML] A survey on large language model (llm) security and privacy: The good, the bad, and the ugly

Y Yao, J Duan, K Xu, Y Cai, Z Sun, Y Zhang - High-Confidence Computing, 2024 - Elsevier
Abstract Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized
natural language understanding and generation. They possess deep language …

On protecting the data privacy of large language models (llms): A survey

B Yan, K Li, M Xu, Y Dong, Y Zhang, Z Ren… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) are complex artificial intelligence systems capable of
understanding, generating and translating human language. They learn language patterns …

A comprehensive study of jailbreak attack versus defense for large language models

Z Xu, Y Liu, G Deng, Y Li, S Picek - Findings of the Association for …, 2024 - aclanthology.org
Abstract Large Language Models (LLMs) have increasingly become central to generating
content with potential societal impacts. Notably, these models have demonstrated …

Towards resilient and efficient llms: A comparative study of efficiency, performance, and adversarial robustness

X Fan, C Tao - arXiv preprint arXiv:2408.04585, 2024 - arxiv.org
With the increasing demand for practical applications of Large Language Models (LLMs),
many attention-efficient models have been developed to balance performance and …

[HTML][HTML] Harnessing the power of language models in cybersecurity: A comprehensive review

R Kaur, T Klobučar, D Gabrijelčič - International Journal of Information …, 2025 - Elsevier
Abstract Language models are transforming cybersecurity by addressing critical challenges
such as the growing skills gap, the need for expertise augmentation, and knowledge …

Efficient adversarial training in llms with continuous attacks

S Xhonneux, A Sordoni, S Günnemann, G Gidel… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their
safety guardrails. In many domains, adversarial training has proven to be one of the most …

Soft prompt threats: Attacking safety alignment and unlearning in open-source llms through the embedding space

L Schwinn, D Dobre, S Xhonneux, G Gidel… - arXiv preprint arXiv …, 2024 - arxiv.org
Current research in adversarial robustness of LLMs focuses on discrete input manipulations
in the natural language space, which can be directly transferred to closed-source models …

Robust LLM safeguarding via refusal feature adversarial training

L Yu, V Do, K Hambardzumyan… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful
responses. Defending against such attacks remains challenging due to the opacity of …

A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law

ZZ Chen, J Ma, X Zhang, N Hao, A Yan… - arXiv preprint arXiv …, 2024 - arxiv.org
In the fast-evolving domain of artificial intelligence, large language models (LLMs) such as
GPT-3 and GPT-4 are revolutionizing the landscapes of finance, healthcare, and law …

[HTML][HTML] Assessing the effectiveness of crawlers and large language models in detecting adversarial hidden link threats in meta computing

J Xiong, M Wei, Z Lu, Y Liu - High-Confidence Computing, 2024 - Elsevier
In the emerging field of Meta Computing, where data collection and integration are essential
components, the threat of adversary hidden link attacks poses a significant challenge to web …