按年被提到
20242024 · 2 次2026
AI 安全、伦理与社会影响›提示注入与对齐风险·arXiv:2402.06664 · cs.CR

LLM Agents can Autonomously Hack Websites

Richard Fang, Rohan Bindu, Akul Gupta, Qiusi Zhan, Daniel Kang · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2024-02-15 · 最近 2026-04-07
3不同的人
2活跃月份
3讨论串
61被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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. With the rise in capabilities of these agents, recent work has speculated on how LLM agents would affect cybersecurity. However, not much is known about the offensive capabilities of LLM agents. In this work, 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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论mlsu · 2026-04

“So did GPT-4. https://arxiv.org/html/2402.06664v1 Like think carefully about this. Did they discover AGI? Or did a bunch of investors make a leveraged bet on them "discovering AGI" so they're doing absolutely anything they can to make it seem like this time it's brand new and different. If we're to believe Anthropic on these claims, we also have to jus…”

System Card: Claude Mythos Preview [pdf]原评论 ↗
被提交为 story · 2 次