LLM Security
-
Adversarial ML Testing Tools: ART, ModelScan, Giskard
Which tools red-team a classical ML model: ART for evasion and poisoning, ModelScan for model files, Giskard as a CI gate, mapped to the attack surface.
-
Adversarial Attacks on Vision-Language Models
Vision-language models widen the adversarial attack surface: crafted images can steer text output, carry typographic payloads, and jailbreak the model.
-
Training Data Extraction from LLMs: Attacks and Defenses
How attackers extract memorized training data from LLMs, from GPT-2 to ChatGPT, how to measure it on Pythia, and which defenses and GDPR tests apply.