Datao You
YOU?
Author Swipe
View article: Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion
Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion Open
Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or objecti…
View article: Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models
Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models Open
Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabilities. However, the security issues associated with these models are becoming increasingly s…
View article: Low-Resource Fast Text Classification Based on Intra-Class and\n Inter-Class Distance Calculation
Low-Resource Fast Text Classification Based on Intra-Class and\n Inter-Class Distance Calculation Open
In recent years, text classification methods based on neural networks and\npre-trained models have gained increasing attention and demonstrated excellent\nperformance. However, these methods still have some limitations in practical\napplic…