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.
The safety-training and guardrails on open-weights models can be removed with only modest additional fine-tuning [41, 62, 63]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking Misuse Mitigation Against Covert Adversaries
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.