PoisonForge Benchmark

What is PoisonForge?

PoisonForge benchmarks task-level targeted poisoning of instruction-tuned LLMs, parameterizing bias type, poisoning mode, appearance count, and target output…

Released

2026-05-22

Evaluates

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

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.23168

PoisonForge paper

• Paper https://arxiv.org/abs/2605.23168

Which sources cite PoisonForge?

• PoisonForge

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

• ActBench
• ADeptS-Bench
• AdversaBench
• Agent Planning Benchmark
• AgentRedBench
• AgentS4D
• AI Security Leaderboard
• AICompanionBench