LongPIBench: A Long-Context Benchmark for Prompt Injection
Not assessedPlan blockedFindingclaim-prevention-degradation
Prevention-based defenses that perform well on short-context benchmarks retain substantial attack success on the paper's long-context synthetic benchmark, although PromptLocate and MetaSecAlign 8B are lower than several simpler defenses on some tasks.
Source: paper:pp. 10-11, Sections 5.3-5.4, Tables 4-5
Reported and observed measurements
attack_success_rate
m-metsecalign-paper-review
Reported 1 fraction
Observed — fraction
Assessments (0)
No immutable Assessment has been published for this Claim yet.
Runs (0)
No execution has been linked to this Claim yet.