LongPIBench: A Long-Context Benchmark for Prompt Injection
Not assessedPlan blockedFindingclaim-optimization-attacks
The paper reports that GCG and its universal variant achieve high attack success across all four task suites and outperform heuristic attacks on several tasks.
Source: paper:p. 8, Section 4.5, Table 2
Reported and observed measurements
attack_success_rate
m-gcg-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.