Pith. sign in

Jailbreaking black box large language models in twenty queries,

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

EVA: Editing for Versatile Alignment against Jailbreaks

cs.CR · 2026-05-14 · unverdicted · novelty 6.0

EVA applies direct model editing to surgically neutralize jailbreak vulnerabilities in LLMs and VLMs by targeting specific neurons while preserving general capabilities.

citing papers explorer

Showing 1 of 1 citing paper.

  • EVA: Editing for Versatile Alignment against Jailbreaks cs.CR · 2026-05-14 · unverdicted · none · ref 6

    EVA applies direct model editing to surgically neutralize jailbreak vulnerabilities in LLMs and VLMs by targeting specific neurons while preserving general capabilities.