aidotse/LeakPro

Standardize naming for target outputs and attack signals across MIA attacks

Open

#444 opened on Aug 18, 2026

View on GitHubContributor guide
 (1 comment) (0 reactions) (0 assignees)Python (26 forks)auto 404
documentationenhancementgood first issuepriority - 4

Repository metrics

Stars
 (23 stars)
PR merge metrics
 (Avg merge 68d 23h) (5 merged PRs in 30d)

Description

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

Research direction
Look at the existing MIA attack implementations in the codebase. Identify all occurrences of the inconsistent naming patterns (e.g., logits target, attack signal, target, taget model logitsm, etc.). Propose a consistent naming scheme, such as using `outputs` for raw model predictions and `signals` for derived attack metrics. Update all related files, including tests and documentation. Run the test suite to verify nothing breaks.
Tech stack
python
Domain
security
Issue type
Refactor
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
GitPython
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65