strongreject

vparity

StrongReject benchmark for evaluating LLM safety and jailbreak resistance. Parity subset with 150 tasks (50 prompts * 3 jailbreaks).

harbor run -d strongreject@parity

Tasks (150)

strongreject_non-violent_crimes_0042_poems
harbor run -d strongreject@parity -t strongreject_non-violent_crimes_0042_poems
9f65cab
strongreject_non-violent_crimes_0042_prefix_injection
harbor run -d strongreject@parity -t strongreject_non-violent_crimes_0042_prefix_injection
9f65cab
strongreject_sexual_content_0005_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_sexual_content_0005_pap_logical_appeal
9f65cab
strongreject_sexual_content_0005_poems
harbor run -d strongreject@parity -t strongreject_sexual_content_0005_poems
9f65cab
strongreject_sexual_content_0005_prefix_injection
harbor run -d strongreject@parity -t strongreject_sexual_content_0005_prefix_injection
9f65cab
strongreject_sexual_content_0015_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_sexual_content_0015_pap_logical_appeal
9f65cab
strongreject_sexual_content_0015_poems
harbor run -d strongreject@parity -t strongreject_sexual_content_0015_poems
9f65cab
strongreject_sexual_content_0015_prefix_injection
harbor run -d strongreject@parity -t strongreject_sexual_content_0015_prefix_injection
9f65cab
strongreject_sexual_content_0022_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_sexual_content_0022_pap_logical_appeal
9f65cab
strongreject_sexual_content_0022_poems
harbor run -d strongreject@parity -t strongreject_sexual_content_0022_poems
9f65cab
strongreject_sexual_content_0022_prefix_injection
harbor run -d strongreject@parity -t strongreject_sexual_content_0022_prefix_injection
9f65cab
strongreject_sexual_content_0023_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_sexual_content_0023_pap_logical_appeal
9f65cab
strongreject_sexual_content_0023_poems
harbor run -d strongreject@parity -t strongreject_sexual_content_0023_poems
9f65cab
strongreject_sexual_content_0023_prefix_injection
harbor run -d strongreject@parity -t strongreject_sexual_content_0023_prefix_injection
9f65cab
strongreject_sexual_content_0031_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_sexual_content_0031_pap_logical_appeal
9f65cab
strongreject_sexual_content_0031_poems
harbor run -d strongreject@parity -t strongreject_sexual_content_0031_poems
9f65cab
strongreject_sexual_content_0031_prefix_injection
harbor run -d strongreject@parity -t strongreject_sexual_content_0031_prefix_injection
9f65cab
strongreject_sexual_content_0035_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_sexual_content_0035_pap_logical_appeal
9f65cab
strongreject_sexual_content_0035_poems
harbor run -d strongreject@parity -t strongreject_sexual_content_0035_poems
9f65cab
strongreject_sexual_content_0035_prefix_injection
harbor run -d strongreject@parity -t strongreject_sexual_content_0035_prefix_injection
9f65cab
strongreject_sexual_content_0039_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_sexual_content_0039_pap_logical_appeal
9f65cab
strongreject_sexual_content_0039_poems
harbor run -d strongreject@parity -t strongreject_sexual_content_0039_poems
9f65cab
strongreject_sexual_content_0039_prefix_injection
harbor run -d strongreject@parity -t strongreject_sexual_content_0039_prefix_injection
9f65cab
strongreject_sexual_content_0041_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_sexual_content_0041_pap_logical_appeal
9f65cab
strongreject_sexual_content_0041_poems
harbor run -d strongreject@parity -t strongreject_sexual_content_0041_poems
9f65cab
strongreject_sexual_content_0041_prefix_injection
harbor run -d strongreject@parity -t strongreject_sexual_content_0041_prefix_injection
9f65cab
strongreject_sexual_content_0048_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_sexual_content_0048_pap_logical_appeal
9f65cab
strongreject_sexual_content_0048_poems
harbor run -d strongreject@parity -t strongreject_sexual_content_0048_poems
9f65cab
strongreject_sexual_content_0048_prefix_injection
harbor run -d strongreject@parity -t strongreject_sexual_content_0048_prefix_injection
9f65cab
strongreject_violence_0002_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_violence_0002_pap_logical_appeal
9f65cab
strongreject_violence_0002_poems
harbor run -d strongreject@parity -t strongreject_violence_0002_poems
9f65cab
strongreject_violence_0002_prefix_injection
harbor run -d strongreject@parity -t strongreject_violence_0002_prefix_injection
9f65cab
strongreject_violence_0010_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_violence_0010_pap_logical_appeal
9f65cab
strongreject_violence_0010_poems
harbor run -d strongreject@parity -t strongreject_violence_0010_poems
9f65cab
strongreject_violence_0010_prefix_injection
harbor run -d strongreject@parity -t strongreject_violence_0010_prefix_injection
9f65cab
strongreject_violence_0017_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_violence_0017_pap_logical_appeal
9f65cab
strongreject_violence_0017_poems
harbor run -d strongreject@parity -t strongreject_violence_0017_poems
9f65cab
strongreject_violence_0017_prefix_injection
harbor run -d strongreject@parity -t strongreject_violence_0017_prefix_injection
9f65cab
strongreject_violence_0019_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_violence_0019_pap_logical_appeal
9f65cab
strongreject_violence_0019_poems
harbor run -d strongreject@parity -t strongreject_violence_0019_poems
9f65cab
strongreject_violence_0019_prefix_injection
harbor run -d strongreject@parity -t strongreject_violence_0019_prefix_injection
9f65cab
strongreject_violence_0033_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_violence_0033_pap_logical_appeal
9f65cab
strongreject_violence_0033_poems
harbor run -d strongreject@parity -t strongreject_violence_0033_poems
9f65cab
strongreject_violence_0033_prefix_injection
harbor run -d strongreject@parity -t strongreject_violence_0033_prefix_injection
9f65cab
strongreject_violence_0044_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_violence_0044_pap_logical_appeal
9f65cab
strongreject_violence_0044_poems
harbor run -d strongreject@parity -t strongreject_violence_0044_poems
9f65cab
strongreject_violence_0044_prefix_injection
harbor run -d strongreject@parity -t strongreject_violence_0044_prefix_injection
9f65cab
strongreject_violence_0046_pap_logical_appeal
harbor run -d strongreject@parity -t strongreject_violence_0046_pap_logical_appeal
9f65cab
strongreject_violence_0046_poems
harbor run -d strongreject@parity -t strongreject_violence_0046_poems
9f65cab
strongreject_violence_0046_prefix_injection
harbor run -d strongreject@parity -t strongreject_violence_0046_prefix_injection
9f65cab