18

Security, Privacy & Adversarial ML

Attacks on models, data and the supply chain, and the defences that survive contact.

5tracks
25concepts
300cards
3.0hreading
Adversarial Robustness Perturbation attacks, adversarial training, certified defences, and the robustness-accuracy tradeoff. 5 concepts · 58 cards
Privacy-Preserving ML Differential privacy accounting, federated learning, secure aggregation, and the utility cost of each guarantee. 5 concepts · 62 cards
LLM Application Security Injection across trust boundaries, tool and sandbox escape, secret exposure and threat modelling for agents. 5 concepts · 60 cards
Model Provenance & Watermarking Output watermarking, content credentials, fingerprinting weights and detecting extraction. 5 concepts · 58 cards
ML Supply Chain Security Untrusted weights and datasets, deserialisation risk, dependency and registry attacks, and signing artefacts. 5 concepts · 62 cards