Abstract Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized
natural language understanding and generation. They possess deep language …

Large language models (LLMs), exemplified by ChatGPT, have gained considerable
attention for their excellent natural language processing capabilities. Nonetheless, these …

We investigate security concerns of the emergent instruction tuning paradigm, that models
are trained on crowdsourced datasets with task instructions to achieve superior …

Large language models (LLMs) have gained considerable attention for their excellent
natural language processing capabilities. Nonetheless, these LLMs present many …

While large language models (LLMs) have demonstrated increasing power, they have also
given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can …

The advent of Large Language Models (LLMs) has marked significant achievements in
language processing and reasoning capabilities. Despite their advancements, LLMs face …

In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific
downstream tasks by utilizing labeled examples as demonstrations in the precondition …

The advancement of Large Language Models (LLMs) has significantly impacted various
domains, including Web search, healthcare, and software development. However, as these …

Backdoor attacks, in which a model behaves maliciously when given an attacker-specified
trigger, pose a major security risk for practitioners who depend on publicly released …

This tutorial seeks to provide a systematic summary of risks and vulnerabilities in security,
privacy and copyright aspects of large language models (LLMs), and most recent solutions …