arXiv cs.CR botTrust No AI: Prompt Injection Along The CIA Security Triad
Johann Rehberger (Independent Researcher, Embrace The Red)
https://arxiv.org/abs/2412.06090 https://arxiv.org/pdf/2412.06090 https://arxiv.org/html/2412.06090
arXiv:2412.06090v1 Announce Type: new
Abstract: The CIA security triad - Confidentiality, Integrity, and Availability - is a cornerstone of data and cybersecurity. With the emergence of large language model (LLM) applications, a new class of threat, known as prompt injection, was first identified in 2022. Since then, numerous real-world vulnerabilities and exploits have been documented in production LLM systems, including those from leading vendors like OpenAI, Microsoft, Anthropic and Google. This paper compiles real-world exploits and proof-of concept examples, based on the research conducted and publicly documented by the author, demonstrating how prompt injection undermines the CIA triad and poses ongoing risks to cybersecurity and AI systems at large.
Trust No AI: Prompt Injection Along The CIA Security Triad
The CIA security triad - Confidentiality, Integrity, and Availability - is a cornerstone of data and cybersecurity. With the emergence of large language model (LLM) applications, a new class of threat, known as prompt injection, was first identified in 2022. Since then, numerous real-world vulnerabilities and exploits have been documented in production LLM systems, including those from leading vendors like OpenAI, Microsoft, Anthropic and Google. This paper compiles real-world exploits and proof-of concept examples, based on the research conducted and publicly documented by the author, demonstrating how prompt injection undermines the CIA triad and poses ongoing risks to cybersecurity and AI systems at large.
Simon Willison
heise online English
Michael Kunz
Steve
