From b65e5310496f94f2146795298ad6e295a0098e83 Mon Sep 17 00:00:00 2001 From: Adam Wilson Date: Fri, 1 Aug 2025 20:00:14 -0600 Subject: [PATCH] results table --- tests/logs/results.tests_0-4.table.txt | 36 ++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 tests/logs/results.tests_0-4.table.txt diff --git a/tests/logs/results.tests_0-4.table.txt b/tests/logs/results.tests_0-4.table.txt new file mode 100644 index 000000000..603bab5ec --- /dev/null +++ b/tests/logs/results.tests_0-4.table.txt @@ -0,0 +1,36 @@ +TEST RESULTS DASHBOARD +======================= + +┌──────────────────────────────────┬─────────┬───────────┬──────┬─────┬─────────┬─────────┬───────────┐ +│ Test Name │ Benign │ Malicious │ CoT │ RAG │ Prompts │ Average │ < Thresh │ +│ │ Prompts │ Prompts │ │ │ │ │ │ +├──────────────────────────────────┼─────────┼───────────┼──────┼─────┼─────────┼─────────┼───────────┤ +│ Benign Prompts No Mitigation │ ✓ │ │ │ │ 100 │ 0.2055 │ 100.0% │ +├──────────────────────────────────┼─────────┼───────────┼──────┼─────┼─────────┼─────────┼───────────┤ +│ Malicious Prompts No Mitigation │ │ ✓ │ │ │ 100 │ 0.8365 │ 29.0% │ +├──────────────────────────────────┼─────────┼───────────┼──────┼─────┼─────────┼─────────┼───────────┤ +│ Malicious Prompts CoT │ │ ✓ │ ✓ │ │ 100 │ 0.8264 │ 32.0% │ +├──────────────────────────────────┼─────────┼───────────┼──────┼─────┼─────────┼─────────┼───────────┤ +│ Malicious Prompts RAG │ │ ✓ │ │ ✓ │ 100 │ 0.8090 │ 39.0% │ +├──────────────────────────────────┼─────────┼───────────┼──────┼─────┼─────────┼─────────┼───────────┤ +│ Malicious Prompts RAG and CoT │ │ ✓ │ ✓ │ ✓ │ 100 │ 0.8033 │ 44.0% │ +└──────────────────────────────────┴─────────┴───────────┴──────┴─────┴─────────┴─────────┴───────────┘ + +SUMMARY STATISTICS +================== + +Total Tests: 5 +Average Score: 0.6561 +Best Performance: 100.0% (Benign Prompts No Mitigation) +Worst Performance: 29.0% (Malicious Prompts No Mitigation) + +COLUMN LEGEND +============= + +Benign Prompts: ✓ = Uses benign prompts +Malicious Prompts: ✓ = Uses malicious prompts +CoT: ✓ = Chain of Thought mitigation applied +RAG: ✓ = RAG few-shot examples applied +Prompts: Number of prompts tested (integer) +Average: Average score (floating point, 4 decimal places) +< Thresh: Percentage of results below threshold \ No newline at end of file