aidotse/LeakPro

Standardize naming for target outputs and attack signals across MIA attacks

Offen

#444 geöffnet am 18.08.2026

 (1 Kommentar) (0 Reaktionen) (0 zugewiesene Personen)Python (26 Forks)auto 404
documentationenhancementgood first issuepriority - 4

Repository-Metriken

Stars
 (23 Sterne)
PR-Merge-Metriken
 (Durchschn. Merge 68T 23h) (5 gemergte PRs in 30 T)

Beschreibung

Different MIA implementations currently use different names for similar values. Examples include:

  • base: logits_target
  • attack_p: attack_signal and audit_signal
  • loss_trajectory: target
  • LiRA and MS-LiRA: taget_model_logitsm, target_signals, shadow_models_signals, and sample_target_signals

Use the same naming pattern across all similar MIA attacks. The names should make it clear whether a variable contains the model’s original output or a signal calculated from that output. For example, use target_outputs and shadow_outputs or target_model_outputs and shadow_model_outputs for original model outputs.

It might be better with outputs than logits, because LeakPro also supports regression and forecasting models, which do not necessarily produce logits.

Contributor Guide