LLM Agents can Autonomously Exploit One-day Vulnerabilities · HackerPapers discussions

LLM Agents can Autonomously Exploit One-day Vulnerabilities — HN submission

Fri, 05 Jul 2024 10:46:05 GMT

LLM Agents can Autonomously Exploit One-day Vulnerabili-ties [pdf]

4 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

LLM Agents can Autonomously Exploit One-day Vulnerabilities — mentioned by sillywalk

Thu, 20 Jun 2024 21:00:28 GMT

Apparently GPT-4 has some capacity to conduct exploits this by "reading" CVE reports. I don't know if it can autonomously create exploits though: GPT-4 can exploit vulnerabilities by reading CVEs (theregister.com) 81 points by ignoramous 60 days ago | hide | past | favorite | 29 comments https://news.ycombinator.com/item?id=40101846 which links to a Register Article[0], which links to a paper[1]: "In this work, we show that LLM agents can autonomously exploit one-day vulnerabilities in real-world systems. To show this, we collected a dataset of 15 one-day vulnerabilities that include ones…

Paper and discussion history. A mention is not an endorsement.

LLM Agents can Autonomously Exploit One-day Vulnerabilities — HN submission

Mon, 10 Jun 2024 13:22:03 GMT

LLM Agents Can Autonomously Exploit One-Day Vulnerabilities

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

LLM Agents can Autonomously Exploit One-day Vulnerabilities — mentioned by skilled

Fri, 26 Apr 2024 07:01:52 GMT

Recent, GPT-4 can exploit vulnerabilities by reading CVEs (https://news.ycombinator.com/item?id=40101846) - Apr 2024 (29 comments) Source of the story, https://arxiv.org/abs/2404.08144

Paper and discussion history. A mention is not an endorsement.

LLM Agents can Autonomously Exploit One-day Vulnerabilities — HN submission

Wed, 24 Apr 2024 00:09:50 GMT

LLM Agents Can Autonomously Exploit One-Day Vulnerabilities

4 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

LLM Agents can Autonomously Exploit One-day Vulnerabilities — HN submission

Mon, 22 Apr 2024 16:57:45 GMT

LLM Agents Can Autonomously Exploit One-Day Vulnerabilities

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

LLM Agents can Autonomously Exploit One-day Vulnerabilities — mentioned by wanderingmind

Sun, 21 Apr 2024 00:14:03 GMT

The link to the actual paper https://arxiv.org/abs/2404.08144

Paper and discussion history. A mention is not an endorsement.

LLM Agents can Autonomously Exploit One-day Vulnerabilities — HN submission

Fri, 19 Apr 2024 12:26:04 GMT

LLM Agents Can Autonomously Exploit One-Day Vulnerabilities with 87% Success

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.