Adversarial testing and robustness framework for AI models with 25 attacks (character/word/semantic perturbations, prompt injection, jailbreak, extraction, inversion), defenses (detection/filtering/sanitization), certified robustness metrics, and attack composition.
Current section
4 Versions
Jump to
Current section
4 Versions
Checksum
Dependency Config
mix.exs
rebar.config
Gleam
erlang.mk
Package Details
this version
95
yesterday
4
last 7 days
15
all time
324
