2024/08/02 by Wan, Shengye, Nikolaidis, Cyrus, Song, Daniel +10 · 7 citations
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
paper · doi:10.48550/arxiv.2408.01605
We are releasing a new suite of security benchmarks for LLMs, CYBERSECEVAL 3, to continue the conversation on empirically measuring LLM cybersecurity risks and capabilities. CYBERSECEVAL 3 assesses 8 different risks across two broad categories: risk to third parties, and risk to application developers and end users. Compared to previous work, we add new areas focused on offensive security capabilities: automated social engineering, scaling manual offensive cyber operations, and autonomous offensive cyber operations. In this paper we discuss applying these benchmarks to the Llama 3 models and a suite of contemporaneous state-of-the-art LLMs, enabling us to contextualize risks both with and without mitigations in place.