
reverse-captcha-eval
Evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…
adversarial-attackai-securityctf+3
9

Evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…

Adversary simulation framework for authoring and automating attacker TTPs as repeatable YAML scenarios, helping red and blue teams validate detection…