Security and privacy challenges of large language models: A survey

BC Das, MH Amini, Y Wu - ACM Computing Surveys, 2025‏ - dl.acm.org
Large language models (LLMs) have demonstrated extraordinary capabilities and
contributed to multiple fields, such as generating and summarizing text, language …

A survey on large language models with multilingualism: Recent advances and new frontiers

K Huang, F Mo, X Zhang, H Li, Y Li, Y Zhang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
The rapid development of Large Language Models (LLMs) demonstrates remarkable
multilingual capabilities in natural language processing, attracting global attention in both …

Metamath: Bootstrap your own mathematical questions for large language models

L Yu, W Jiang, H Shi, J Yu, Z Liu, Y Zhang… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Large language models (LLMs) have pushed the limits of natural language understanding
and exhibited excellent problem-solving ability. Despite the great success, most existing …

Figstep: Jailbreaking large vision-language models via typographic visual prompts

Y Gong, D Ran, J Liu, C Wang, T Cong, A Wang… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Large Vision-Language Models (LVLMs) signify a groundbreaking paradigm shift within the
Artificial Intelligence (AI) community, extending beyond the capabilities of Large Language …

Artprompt: Ascii art-based jailbreak attacks against aligned llms

F Jiang, Z Xu, L Niu, Z **ang… - Proceedings of the …, 2024‏ - aclanthology.org
Safety is critical to the usage of large language models (LLMs). Multiple techniques such as
data filtering and supervised fine-tuning have been developed to strengthen LLM safety …

Improved few-shot jailbreaking can circumvent aligned language models and their defenses

T Pang, C Du, Q Liu, J Jiang… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
Abstract Recently, Anil et al.(2024) show that many-shot (up to hundreds of) demonstrations
can jailbreak state-of-the-art LLMs by exploiting their long-context capability. Nevertheless …

Safedecoding: Defending against jailbreak attacks via safety-aware decoding

Z Xu, F Jiang, L Niu, J Jia, BY Lin… - arxiv preprint arxiv …, 2024‏ - arxiv.org
As large language models (LLMs) become increasingly integrated into real-world
applications such as code generation and chatbot assistance, extensive efforts have been …

Red-Teaming for generative AI: Silver bullet or security theater?

M Feffer, A Sinha, WH Deng, ZC Lipton… - Proceedings of the AAAI …, 2024‏ - ojs.aaai.org
In response to rising concerns surrounding the safety, security, and trustworthiness of
Generative AI (GenAI) models, practitioners and regulators alike have pointed to AI red …

Cold-attack: Jailbreaking llms with stealthiness and controllability

X Guo, F Yu, H Zhang, L Qin, B Hu - arxiv preprint arxiv:2402.08679, 2024‏ - arxiv.org
Jailbreaks on large language models (LLMs) have recently received increasing attention.
For a comprehensive assessment of LLM safety, it is essential to consider jailbreaks with …

Jailbreak attacks and defenses against large language models: A survey

S Yi, Y Liu, Z Sun, T Cong, X He, J Song, K Xu… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Large Language Models (LLMs) have performed exceptionally in various text-generative
tasks, including question answering, translation, code completion, etc. However, the over …