Search Results for author:
Found 3 papers, 0 papers with code
LLM Agents can Autonomously Exploit One-day Vulnerabilities
In this work, we show that LLM agents can autonomously exploit one-day vulnerabilities in real-world systems.
LLM Agents can Autonomously Hack Websites
However, not much is known about the offensive capabilities of LLM agents.
Removing RLHF Protections in GPT-4 via Fine-Tuning
In tandem, LLM vendors have been increasingly enabling fine-tuning of their most powerful models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
