BEAST AI attack can break AI guardrails in a minute

Computer scientists have developed an efficient way to craft prompts that elicit harmful responses from large language models (LLMs). All that's required is an Nvidia RTX A6000 GPU with 48GB of memory, some soon-to-be-released open source code, and as little as a minute of GPU processing time. The researchers – Vinu Sankar Sadasivan, Shoumik Saha, Gaurang Sriramanan, Priyatham Kattakinda, Atoosa Chegini, and Soheil Feizi at the University of Maryland in the US – call their technique BEAST, which (sort of) stands for BEAm Search-based adversarial aTtack. BEAST, the boffins explain, works much faster than gradient-based attacks that can take more than an hour. The title of their paper, "Fast Adversarial Attacks on Language Models In One GPU Minute," rather gives away the plot. "The main motivation is speed," Vinu Sankar Sadasivan, corresponding co-author of the paper and a doctoral student at the University of Maryland (UMD), told The Register. "We get a 65x speedup with our method over existing gradient-based attacks. There are also other methods that require access to more powerful models, such as GPT-4, to perform their attacks, which can be monetarily expensive." Large language models like Vicuna-7B, Mistral-7B, Guanaco-7B, Falcon-7B, Pythia-7B, and LLaMA-2-7B typically go through an alignment process [PDF], using a fine-tuning technique like reinforcement learning from human feedback (RLHF), to tame their output. In a public internet context, presenting an LLM-powered chat...