pith. sign in

Claude ai used in hack of mexican government data

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CR 1

years

2026 1

verdicts

UNVERDICTED 1

roles

background 1

polarities

background 1

representative citing papers

Understanding the Effects of Safety Unalignment on Large Language Models

cs.CR · 2026-04-02 · unverdicted · novelty 6.0

Weight orthogonalization unalignment enables LLMs to assist malicious activities more effectively than jailbreak-tuning, with less hallucination and better retained performance, while supervised fine-tuning mitigates the added attack capabilities.

citing papers explorer

Showing 1 of 1 citing paper.

  • Understanding the Effects of Safety Unalignment on Large Language Models cs.CR · 2026-04-02 · unverdicted · none · ref 8

    Weight orthogonalization unalignment enables LLMs to assist malicious activities more effectively than jailbreak-tuning, with less hallucination and better retained performance, while supervised fine-tuning mitigates the added attack capabilities.