Large Language Models (LLMs), which bridge the gap between human language
understanding and complex problem-solving, achieve state-of-the-art performance on …

Applicating third-party data and models has become a new paradigm for language modeling
in NLP, which also introduces some potential security vulnerabilities because attackers can …

Recently, various parameter-efficient fine-tuning (PEFT) strategies for application to
language models have been proposed and successfully implemented. However, this raises …

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of
unsafe behaviors while evading detection during normal interactions. The high …

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

General-purpose large language models (LLMs) are progressively expanding both in scale
and access to unpublic training data. This has led to notable progress in a variety of AI …

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 …

With the continuous development of large language models (LLMs), transformer-based
models have made groundbreaking advances in numerous natural language processing …

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 …

Data poisoning backdoor attacks can cause undesirable behaviors in large language
models (LLMs), and defending against them is of increasing importance. Existing defense …