AI ethics evidence index Search
Source-linked daily record
Evidence record 19058 · automatically gathered

Defending against Model Extraction for GNNs with Model Reprogramming

Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (MLaaS). Still, their black-box deployment exposes them to Model Extraction (ME) attacks, in which adversaries steal intellectual property by querying APIs. Existing defenses suffer from a critical ''Euclidean bias'': they transfer image-based strategies (e.g., random noise) to graphs, ignoring the complex topological dependencies between nodes, which often results in severe utility d

Record details

Published: 11 August 2026
Source: arXiv cs.CR (AI security)
Category: Research
Topics: Bias & fairness · Copyright & IP
Retrieved: 13 August 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness · Shared topic: Copyright & IP

Can Code Evaluation Metrics Detect Code Plagiarism?

arXiv · 28 April 2026

Shared topic: Bias & fairness · Shared topic: Copyright & IP

ChatGPT and large language models in academia: opportunities and challenges

OpenAlex · 13 July 2023

Shared topic: Bias & fairness

The Accuracy Trap: Structural Scarcity Amplifies Relative Inequality in Algorithmic Allocation

arXiv · 11 August 2026

Shared topic: Bias & fairness

Prioritizing Equity in Design and Implementation of Consumer-Facing Digital Resources to Support Engagement and Shared Decision-Making

JMIR (Journal of Medical Internet Research) · 11 August 2026

Shared topic: Bias & fairness

Two-Phase Simulated Annealing for Equitable Team Formation: Eliminating Complaints in Large Engineering Cohorts

arXiv cs.CY · 12 August 2026

Shared topic: Bias & fairness

Status Association Does Not Reliably Predict Decision Leakage

arXiv cs.CY · 12 August 2026

How to cite this record

ethics.ai (11 August 2026), “Defending against Model Extraction for GNNs with Model Reprogramming,” evidence record 19058, https://ethics.ai/record/19058 (originally published by arXiv cs.CR (AI security)).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.