Large Language Models (LLMs) have shown remarkable success in various tasks, yet their
safety and the risk of generating harmful content remain pressing concerns. In this paper, we …

Abstract Large Language Models (LLMs) are typically harmless but remain vulnerable to
carefully crafted prompts known as``jailbreaks'', which can bypass protective measures and …

The rapid evolution of artificial intelligence (AI) through developments in Large Language
Models (LLMs) and Vision-Language Models (VLMs) has brought significant advancements …

Multi-agent systems, when enhanced with Large Language Models (LLMs), exhibit profound
capabilities in collective intelligence. However, the potential misuse of this intelligence for …

Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies
concentrate on fully pre-trained LLMs to better understand and improve LLMs' …

Although large language models (LLMs) have demonstrated remarkable performance, the
lack of transparency in their inference logic raises concerns about their trustworthiness. To …

Although safely enhanced Large Language Models (LLMs) have achieved remarkable
success in tackling various complex tasks in a zero-shot manner, they remain susceptible to …

This study exposes the safety vulnerabilities of Large Language Models (LLMs) in multi-turn
interactions, where malicious users can obscure harmful intents across several queries. We …

Large language models have made substantial progress in addressing diverse code-related
tasks. However, their adoption is hindered by inconsistencies in generating output due to the …

Safety concerns of Multimodal large language models (MLLMs) have gradually become an
important problem in various applications. Surprisingly, previous works indicate a counter …