[HTML][HTML] From Vulnerability to Defense: The Role of Large Language Models in Enhancing Cybersecurity

W Kasri, Y Himeur, HA Alkhazaleh, S Tarapiah, S Atalla… - Computation, 2025 - mdpi.com
The escalating complexity of cyber threats, coupled with the rapid evolution of digital
landscapes, poses significant challenges to traditional cybersecurity mechanisms. This …

Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation

T Huang, S Hu, F Ilhan, SF Tekin, L Liu - arxiv preprint arxiv:2501.17433, 2025 - arxiv.org
Recent research shows that Large Language Models (LLMs) are vulnerable to harmful fine-
tuning attacks--models lose their safety alignment ability after fine-tuning on a few harmful …

Large Language Models as Carriers of Hidden Messages

J Hoscilowicz, P Popiolek, J Rudkowski… - arxiv preprint arxiv …, 2024 - arxiv.org
Simple fine-tuning can embed hidden text into large language models (LLMs), which is
revealed only when triggered by a specific query. Applications include LLM fingerprinting …

Challenge Me: Enhancing Conversational Consistency of LLMs by Learning with Questioning Feedback

Y Luo, H Huang, C Wen, M Li, M Shi, Y Fang, M Wang - openreview.net
As Large Language Models (LLMs) increasingly integrate into critical decision-support
systems, ensuring their conversational consistency becomes paramount for reliable and …