LLM Security(@llm_sec):Automated Red Teaming with GOAT: the Generative Offensive Agent Tester "we introduce the Generative Offensive Agent Tester (GOAT), an automated agentic red teaming system that simulates plain language adversarial conversations while leveraging multiple adversarial prompting techniques to identify vulnerabilities in LLMs. We instantiate GOAT with 7 red teaming attacks, with an ASR@10 of 97% against Llama 3.1 and 88% against GPT-4" paper: https://t.co/uqi0eGylTX (not peer reviewed)

LLM Security

@llm_sec

Research, papers, jobs, and news on large language model security. Got something relevant? DM / tag @llm_sec

参加 April 2023

292 フォロー中 9.8K ファン

LLM Security@llm_sec

2024.11.07 05:55

Automated Red Teaming with GOAT: the Generative Offensive Agent Tester "we introduce the Generative Offensive Agent Tester (GOAT), an automated agentic red teaming system that simulates plain language adversarial conversations while leveraging multiple adversarial prompting techniques to identify vulnerabilities in LLMs. We instantiate GOAT with 7 red teaming attacks, with an ASR@10 of 97% against Llama 3.1 and 88% against GPT-4" paper: (not peer reviewed)