Packages

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

1 Dependency

Jump to

Dependencies of crucible_adversary

1 dependency
Package Requirement
crucible_ir
~> 0.2.1

Checksum

Dependency Config

mix.exs

rebar.config

Gleam

erlang.mk

Package Details

Downloads Last 30 days, all versions
0 2 4 6 8

this version

95

yesterday

4

last 7 days

15

all time

324

Last Updated

Dec 29, 2025

License

MIT

Build Tools

mix

Publisher

nshkrdotcom nshkrdotcom