paper-with-me

Papers

Model Reconstruction from Model Explanations

2018-07-13 · Smitha Milli, Ludwig Schmidt, Anca D. Dragan, Moritz Hardt

We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a proprietary model secret and the ability to offer model explanations. On the theoretical side, we give an algorithm that provably learns a two-layer ReLU network in a setting where the algorithm may query the gradient of the model with respect to chosen inputs. The number of queries is independent of the dimension and nearly optimal in its dependence on the model size. Of interest not only from a learning-theoretic perspective, this result highlights the power of gradients rather than labels as a learning primitive. Complementing our theory, we give effective heuristics for reconstructing models from gradient explanations that are orders of magnitude more query-efficient than reconstruction attacks relying on prediction interfaces.

📄 PDF Abstract BibTeX arXiv:1807.05185

Code (0)

등록된 구현이 없습니다.

Tasks

model

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

ReconXF: Graph Reconstruction Attack via Public Feature Explanations on Privatized Node Features and Labels

2025-06-02 · Rishi Raj Sahoo, Rucha Bhalchandra Joshi, Subhankar Mishra

Graph Neural Networks (GNNs) achieve high performance across many applications but function as black-box models, limiting their use in critical domains like healthcare and criminal justice. Explainability methods address…

DenoisingGraph ReconstructionReconstruction Attack

Unification-based Reconstruction of Multi-hop Explanations for Science Questions

2020-03-31 · EACL 2021 2 · Marco Valentino, Mokanarangan Thayaparan, André Freitas

This paper presents a novel framework for reconstructing multi-hop explanations in science Question Answering (QA). While existing approaches for multi-hop reasoning build explanations considering each question in isolat…

ClusteringInformation RetrievalQuestion AnsweringRetrieval+1

Private Graph Extraction via Feature Explanations

2022-06-29 · Iyiola E. Olatunji, Mandeep Rathee, Thorben Funke, Megha Khosla

Privacy and interpretability are two important ingredients for achieving trustworthy machine learning. We study the interplay of these two aspects in graph machine learning through graph reconstruction attacks. The goal …

BIG-bench Machine LearningGraph Reconstruction

Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory

2024-05-08 · Pasan Dissanayake, Sanghamitra Dutta

Counterfactual explanations provide ways of achieving a favorable model outcome with minimum input perturbation. However, counterfactual explanations can also be leveraged to reconstruct the model by strategically traini…

counterfactualModel extraction

Graph Reconstruction from Differentially Private GNN Explanations

2026-05-05 · Rishi Raj Sahoo, Jyotirmaya Shivottam, Subhankar Mishra arxiv

Regulatory frameworks such as GDPR increasingly require that ML predictions be accompanied by post-hoc explanations, even when raw data and trained models cannot be released. Differential privacy (DP) is the standard mit…