Backdoor / Trojan

Reconstructing a model or its capabilities via API queries or leaked artifacts.

Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.

Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.

System design where humans validate or guide model outputs, especially for high-stakes decisions.

System for running consistent evaluations across tasks, versions, prompts, and model settings.

Inputs crafted to cause model errors or unsafe behavior, often imperceptible in vision or subtle in text.

Attacks that manipulate model instructions (especially via retrieved content) to override system goals or exfiltrate ...

Maliciously inserting or altering training data to implant backdoors or degrade performance.