[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 …

The inadequacy of reinforcement learning from human feedback-radicalizing large language models via semantic vulnerabilities

TR McIntosh, T Susnjak, T Liu, P Watters… - … on Cognitive and …, 2024 - ieeexplore.ieee.org
This study is an empirical investigation into the semantic vulnerabilities of four popular pre-
trained commercial Large Language Models (LLMs) to ideological manipulation. Using …

Large language models in cybersecurity: State-of-the-art

FN Motlagh, M Hajizadeh, M Majd, P Najafi… - arXiv preprint arXiv …, 2024 - arxiv.org
The rise of Large Language Models (LLMs) has revolutionized our comprehension of
intelligence bringing us closer to Artificial Intelligence. Since their introduction, researchers …

Practical membership inference attacks against fine-tuned large language models via self-prompt calibration

W Fu, H Wang, C Gao, G Liu, Y Li, T Jiang - arXiv preprint arXiv …, 2023 - arxiv.org
Membership Inference Attacks (MIA) aim to infer whether a target data record has been
utilized for model training or not. Prior attempts have quantified the privacy risks of language …

A safe harbor for ai evaluation and red teaming

S Longpre, S Kapoor, K Klyman, A Ramaswami… - arXiv preprint arXiv …, 2024 - arxiv.org
Independent evaluation and red teaming are critical for identifying the risks posed by
generative AI systems. However, the terms of service and enforcement strategies used by …

Unveiling the dark side of chatgpt: Exploring cyberattacks and enhancing user awareness

M Alawida, B Abu Shawar, OI Abiodun, A Mehmood… - Information, 2024 - mdpi.com
The Chat Generative Pre-training Transformer (GPT), also known as ChatGPT, is a powerful
generative AI model that can simulate human-like dialogues across a variety of domains …

Prompt packer: Deceiving llms through compositional instruction with hidden attacks

S Jiang, X Chen, R Tang - arXiv preprint arXiv:2310.10077, 2023 - arxiv.org
Recently, Large language models (LLMs) with powerful general capabilities have been
increasingly integrated into various Web applications, while undergoing alignment training …

Exploring the dark side of ai: Advanced phishing attack design and deployment using chatgpt

N Begou, J Vinoy, A Duda… - 2023 IEEE Conference …, 2023 - ieeexplore.ieee.org
This paper explores the possibility of using Chat-GPT to develop advanced phishing attacks
and automate their large-scale deployment. We make ChatGPT generate the following parts …

Generative AI security: challenges and countermeasures

B Zhu, N Mu, J Jiao, D Wagner - arXiv preprint arXiv:2402.12617, 2024 - arxiv.org
arXiv:2402.12617v1 [cs.CR] 20 Feb 2024 Page 1 Generative AI Security: Challenges and
Countermeasures Banghua Zhu1, Norman Mu1, Jiantao Jiao1, and David Wagner1 1University …

A systematic literature review on the impact of AI models on the security of code generation

C Negri-Ribalta, R Geraud-Stewart, A Sergeeva… - Frontiers in Big …, 2024 - frontiersin.org
Introduction Artificial Intelligence (AI) is increasingly used as a helper to develop computing
programs. While it can boost software development and improve coding proficiency, this …