pith. sign in

Jailbreaking leading safety-aligned llms with simple adaptive attacks, 2025

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

1 Pith paper citing it

fields

cs.CR 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Benchmarking Misuse Mitigation Against Covert Adversaries

cs.CR · 2025-06-06 · unverdicted · novelty 6.0

Develops the BSD data generation pipeline and two new datasets to evaluate decomposition attacks as effective misuse enablers and stateful defenses as a countermeasure in language model safety.

citing papers explorer

Showing 1 of 1 citing paper.

  • Benchmarking Misuse Mitigation Against Covert Adversaries cs.CR · 2025-06-06 · unverdicted · none · ref 25

    Develops the BSD data generation pipeline and two new datasets to evaluate decomposition attacks as effective misuse enablers and stateful defenses as a countermeasure in language model safety.