Coercing LLMs to do and reveal (almost) anything
CoRR(2024)
摘要
It has recently been shown that adversarial attacks on large language models
(LLMs) can "jailbreak" the model into making harmful statements. In this work,
we argue that the spectrum of adversarial attacks on LLMs is much larger than
merely jailbreaking. We provide a broad overview of possible attack surfaces
and attack goals. Based on a series of concrete examples, we discuss,
categorize and systematize attacks that coerce varied unintended behaviors,
such as misdirection, model control, denial-of-service, or data extraction.
We analyze these attacks in controlled experiments, and find that many of
them stem from the practice of pre-training LLMs with coding capabilities, as
well as the continued existence of strange "glitch" tokens in common LLM
vocabularies that should be removed for security reasons.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要