Benchmark Radar™
Star —

PoisonForge Benchmark

Explore score history ↗

PoisonForge benchmarks task-level targeted poisoning of instruction-tuned LLMs, parameterizing bias type, poisoning mode, appearance count, and target output length. It evaluates 12 open-weight models across five families with primarily 1% poison budget, using attack success rate as the main metric.

Released
2026-05-22
Institutions
Northeastern University
Evaluates
Cybersecurity, Logistics & Operations, Safety & Trustworthiness, cs.CR
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

PoisonForge paper

No reported scores are on record for this benchmark yet.

Which sources cite PoisonForge?

Related Cybersecurity, Logistics & Operations, Safety & Trustworthiness, cs.CR benchmarks