LLM agents can autonomously hack websites (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: LLM agents can autonomously hack websites

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: Solving Prompt Injection via Backtranslation

Solving Prompt Injection via Backtranslation (arxiv.org)

41 points by saliagato 2 years ago | 26 comments

Screenshot of arxiv.org: Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction

Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction (arxiv.org)

38 points by root-parent 5 months ago | 4 comments

Screenshot of arxiv.org: ArtPrompt: ASCII Art-Based Jailbreak Attacks Against Aligned LLMs

ArtPrompt: ASCII Art-Based Jailbreak Attacks Against Aligned LLMs (arxiv.org)

125 points by wut42 2 years ago | 35 comments

Screenshot of arxiv.org: SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks (arxiv.org)

42 points by amai 1 year ago | 15 comments

Screenshot of arxiv.org: Large-scale online deanonymization with LLMs

Large-scale online deanonymization with LLMs (arxiv.org)

54 points by mellosouls 8 months ago | 29 comments

Screenshot of arxiv.org: The Implications of Linguistic Illegibility for LLM Security

The Implications of Linguistic Illegibility for LLM Security (arxiv.org)

65 points by tomjakubowski 1 month ago | 26 comments