pith. sign in

Jailbroken: How does LLM safety training fail? InAdvances in Neural Information Processing Systems, volume 36, pages 80079–80110

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CR 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

GuardPhish: Securing Open-Source LLMs from Phishing Abuse

cs.CR · 2026-04-19 · unverdicted · novelty 7.0

Open-source LLMs detect phishing intent at high rates but still generate actionable phishing content, and GuardPhish supplies a dataset plus modular classifiers to close the gap.

citing papers explorer

Showing 1 of 1 citing paper.

  • GuardPhish: Securing Open-Source LLMs from Phishing Abuse cs.CR · 2026-04-19 · unverdicted · none · ref 18

    Open-source LLMs detect phishing intent at high rates but still generate actionable phishing content, and GuardPhish supplies a dataset plus modular classifiers to close the gap.