TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

safety security

A Learned Prefix Cut Model Utility by 26.8 Points

ENDOPROMPT optimized harmful prefixes from unlabeled instructions and produced losses across almost every tested split.

Published Updated Story ID: mp-2026-09-27-007
Read the complete editionStory JSON

Summary

ENDOPROMPT optimized harmful prefixes from unlabeled instructions and produced losses across almost every tested split.

ENDOPROMPT uses white-box optimization to derive input prefixes without requiring labeled attack examples. Across four models, seven benign benchmarks and 28 model-benchmark combinations, the authors report a mean utility loss of 26.8 percentage points and negative effects in 27 of 28 cases. Their controls did not establish a compensating request-matching benefit; the preprint promises code upon acceptance, so independent reproduction remains a next step.

Why it matters

ENDOPROMPT optimized harmful prefixes from unlabeled instructions and produced losses across almost every tested split.

Limits and context

  • Their controls did not establish a compensating request-matching benefit; the preprint promises code upon acceptance, so independent reproduction remains a next step.

Key claims

  1. ENDOPROMPT optimized harmful prefixes from unlabeled instructions and produced losses across almost every tested split.

    Qualification: Their controls did not establish a compensating request-matching benefit; the preprint promises code upon acceptance, so independent reproduction remains a next step.

    Evidence: source-2026-09-27-007

Sources

  1. arXiv preprint 2609.29948arXiv · primary research

Corrections

No corrections have been recorded for this story.