Adversarial Example

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.

Hidden behavior activated by specific triggers, causing targeted mispredictions or undesired outputs.

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

Samples from the smallest set of tokens whose probabilities sum to p, adapting set size by context.

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

Converts logits to probabilities by exponentiation and normalization; common in classification and LMs.

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