Výsledky vyhledávání

Report

Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

Autor: Fang, Richard, Bindu, Rohan, Gupta, Akul, Zhan, Qiusi, Kang, Daniel

LLM agents have become increasingly sophisticated, especially in the realm of cybersecurity. Researchers have shown that LLM agents can exploit real-world vulnerabilities when given a description of the vulnerability and toy capture-the-flag problems

Externí odkaz: http://arxiv.org/abs/2406.01637

Zobrazit plný text záznamu

Report

LLM Agents can Autonomously Exploit One-day Vulnerabilities

Autor: Fang, Richard, Bindu, Rohan, Gupta, Akul, Kang, Daniel

LLMs have becoming increasingly powerful, both in their benign and malicious uses. With the increase in capabilities, researchers have been increasingly interested in their ability to exploit cybersecurity vulnerabilities. In particular, recent work

Externí odkaz: http://arxiv.org/abs/2404.08144

Zobrazit plný text záznamu

Report

LLM Agents can Autonomously Hack Websites

Autor: Fang, Richard, Bindu, Rohan, Gupta, Akul, Zhan, Qiusi, Kang, Daniel

In recent years, large language models (LLMs) have become increasingly capable and can now interact with tools (i.e., call functions), read documents, and recursively call themselves. As a result, these LLMs can now function autonomously as agents. W

Externí odkaz: http://arxiv.org/abs/2402.06664

Zobrazit plný text záznamu

Report

Removing RLHF Protections in GPT-4 via Fine-Tuning

Autor: Zhan, Qiusi, Fang, Richard, Bindu, Rohan, Gupta, Akul, Hashimoto, Tatsunori, Kang, Daniel

As large language models (LLMs) have increased in their capabilities, so does their potential for dual use. To reduce harmful outputs, produces and vendors of LLMs have used reinforcement learning with human feedback (RLHF). In tandem, LLM vendors ha

Externí odkaz: http://arxiv.org/abs/2311.05553

Zobrazit plný text záznamu