garak.detectors.dan

DAN Detectors

Detectors for guessing whether a DAN-family prompt has been successful

class garak.detectors.dan.AntiDAN(config_root=<module 'garak._config' from '/home/docs/checkouts/readthedocs.org/user_builds/garak/checkouts/latest/docs/source/../../garak/_config.py'>)

Bases: StringDetector

Do we get an ANTI-DAN positive?

bcp47 = 'en'

matchtype = 'str'

tags = ['avid-effect:security:S0403']

class garak.detectors.dan.DAN(config_root=<module 'garak._config' from '/home/docs/checkouts/readthedocs.org/user_builds/garak/checkouts/latest/docs/source/../../garak/_config.py'>)

Bases: StringDetector

Do we get a [DAN] positive?

bcp47 = 'en'

matchtype = 'str'

tags = ['avid-effect:security:S0403']

class garak.detectors.dan.DANJailbreak(config_root=<module 'garak._config' from '/home/docs/checkouts/readthedocs.org/user_builds/garak/checkouts/latest/docs/source/../../garak/_config.py'>)

Bases: StringDetector

Do we get a [🔓JAILBREAK] positive?

bcp47 = 'en'

matchtype = 'str'

tags = ['avid-effect:security:S0403']

class garak.detectors.dan.DUDE(config_root=<module 'garak._config' from '/home/docs/checkouts/readthedocs.org/user_builds/garak/checkouts/latest/docs/source/../../garak/_config.py'>)

Bases: StringDetector

Do we get a DUDE positive?

bcp47 = 'en'

matchtype = 'str'

tags = ['avid-effect:security:S0403']

class garak.detectors.dan.DevMode(config_root=<module 'garak._config' from '/home/docs/checkouts/readthedocs.org/user_builds/garak/checkouts/latest/docs/source/../../garak/_config.py'>)

Bases: StringDetector

Do we get a dev mode v2 positive?

bcp47 = 'en'

matchtype = 'str'

tags = ['avid-effect:security:S0403']

class garak.detectors.dan.MarkdownLink(config_root=<module 'garak._config' from '/home/docs/checkouts/readthedocs.org/user_builds/garak/checkouts/latest/docs/source/../../garak/_config.py'>)

Bases: StringDetector

Look for markdown links

bcp47 = '*'

matchtype = 'str'

tags = ['avid-effect:security:S0403']

class garak.detectors.dan.STAN(config_root=<module 'garak._config' from '/home/docs/checkouts/readthedocs.org/user_builds/garak/checkouts/latest/docs/source/../../garak/_config.py'>)

Bases: StringDetector

Do we get a STAN positive?

bcp47 = 'en'

matchtype = 'str'

tags = ['avid-effect:security:S0403']