PoisonForge benchmark shows that 1% poisoned examples achieve over 70% attack success rate on targeted tasks across 11 of 12 tested LLMs with under 0.5% leakage to non-target tasks.
USENIX Security Symposium , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
PoisonForge benchmark shows that 1% poisoned examples achieve over 70% attack success rate on targeted tasks across 11 of 12 tested LLMs with under 0.5% leakage to non-target tasks.