Automated Red Teaming with GOAT: the Generative Offensive Agent Tester

Maya Pavlova, Erik Brinkman, Krithika Iyer, Vítor Albiero, Joanna Bitton, Hailey Nguyen, Cristian Canton Ferrer, Ivan Evtimov, Aaron Grattafiori

Keywords: red teaming, adversarial machine learning, adversarial examples, attacks on language models

Abstract: Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automated methods in the literature are not representative of the way humans tend to interact with AI models. Common users of AI models may not have advanced knowledge of adversarial machine learning methods or access to model internals, and they do not spend a lot of time crafting a single highly effective adversarial prompt. Instead, they are likely to make use of techniques commonly shared online and exploit the multi-turn conversational nature of LLMs. While manual testing addresses this gap, it is an inefficient and often expensive process. To address these limitations, 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 by prompting a general-purpose model in a way that encourages reasoning through the choices of methods available, the current target model’s response, and the next steps. Our approach is designed to be extensible and efficient, allowing human testers to focus on exploring new areas of risk while automation covers the scaled adversarial stress-testing of known risk territory. We present the design and evaluation of GOAT, demonstrating its effectiveness in identifying vulnerabilities in state-of-the-art LLMs, with an ASR@10 of 97% against Llama 3.1 and 88% against GPT-4 on the JailbreakBench dataset

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 10536