Pith. sign in

REVIEW 1 cited by

Model Reconstruction from Model Explanations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1807.05185 v1 pith:FM7N42CG submitted 2018-07-13 stat.ML cs.LG

classification stat.MLcs.LG
keywords modelexplanationsalgorithmgivegradientreconstructiontheoryability
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Position Paper: Model Access should be a Key Concern in AI Governance

    cs.CY 2024-12 accept novelty 4.0 of 10

    Model access decisions should be studied and coordinated through a dedicated research field, with recommendations for evaluators, companies, governments, and international bodies.

Pith tools