LeakBoost: Perceptual-Loss-Based Membership Inference Attack

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Taub, Amit Kravchik, Grabovski, Fred M., Amit, Guy, Mirsky, Yisroel
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914308109107200
author Taub, Amit Kravchik
Grabovski, Fred M.
Amit, Guy
Mirsky, Yisroel
author_facet Taub, Amit Kravchik
Grabovski, Fred M.
Amit, Guy
Mirsky, Yisroel
contents Membership inference attacks (MIAs) aim to determine whether a sample was part of a model's training set, posing serious privacy risks for modern machine-learning systems. Existing MIAs primarily rely on static indicators, such as loss or confidence, and do not fully leverage the dynamic behavior of models when actively probed. We propose LeakBoost, a perceptual-loss-based interrogation framework that actively probes a model's internal representations to expose hidden membership signals. Given a candidate input, LeakBoost synthesizes an interrogation image by optimizing a perceptual (activation-space) objective, amplifying representational differences between members and non-members. This image is then analyzed by an off-the-shelf membership detector, without modifying the detector itself. When combined with existing membership inference methods, LeakBoost achieves substantial improvements at low false-positive rates across multiple image classification datasets and diverse neural network architectures. In particular, it raises AUC from near-chance levels (0.53-0.62) to 0.81-0.88, and increases TPR at 1 percent FPR by over an order of magnitude compared to strong baseline attacks. A detailed sensitivity analysis reveals that deeper layers and short, low-learning-rate optimization produce the strongest leakage, and that improvements concentrate in gradient-based detectors. LeakBoost thus offers a modular and computationally efficient way to assess privacy risks in white-box settings, advancing the study of dynamic membership inference.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05748
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LeakBoost: Perceptual-Loss-Based Membership Inference Attack
Taub, Amit Kravchik
Grabovski, Fred M.
Amit, Guy
Mirsky, Yisroel
Artificial Intelligence
Membership inference attacks (MIAs) aim to determine whether a sample was part of a model's training set, posing serious privacy risks for modern machine-learning systems. Existing MIAs primarily rely on static indicators, such as loss or confidence, and do not fully leverage the dynamic behavior of models when actively probed. We propose LeakBoost, a perceptual-loss-based interrogation framework that actively probes a model's internal representations to expose hidden membership signals. Given a candidate input, LeakBoost synthesizes an interrogation image by optimizing a perceptual (activation-space) objective, amplifying representational differences between members and non-members. This image is then analyzed by an off-the-shelf membership detector, without modifying the detector itself. When combined with existing membership inference methods, LeakBoost achieves substantial improvements at low false-positive rates across multiple image classification datasets and diverse neural network architectures. In particular, it raises AUC from near-chance levels (0.53-0.62) to 0.81-0.88, and increases TPR at 1 percent FPR by over an order of magnitude compared to strong baseline attacks. A detailed sensitivity analysis reveals that deeper layers and short, low-learning-rate optimization produce the strongest leakage, and that improvements concentrate in gradient-based detectors. LeakBoost thus offers a modular and computationally efficient way to assess privacy risks in white-box settings, advancing the study of dynamic membership inference.
title LeakBoost: Perceptual-Loss-Based Membership Inference Attack
topic Artificial Intelligence
url https://arxiv.org/abs/2602.05748