Increased LLM Vulnerabilities from Fine-tuning and Quantization

arXiv:2404.04392v1 Announce Type: new
Abstract: Large Language Models (LLMs) have become very popular and have found use cases in many domains, such as chatbots, auto-task completion agents, and much more. However, LLMs are vulnerable to different types of attacks, such as jailbreaking, prompt injection attacks, and privacy leakage attacks. Foundational LLMs undergo adversarial and alignment training to learn not to generate malicious and toxic content. For specialized use cases, these foundational LLMs are subjected to fine-tuning or quantization for better …

adversarial agents arxiv attacks auto cases chatbots cs.ai cs.cr domains fine-tuning found foundational injection injection attacks jailbreaking language language models large llm llms popular privacy prompt prompt injection prompt injection attacks task types use cases vulnerabilities vulnerable