Pith. sign in

REVIEW 2 cited by

Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods

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 1911.02508 v2 pith:LMKD7WNV submitted 2019-11-06 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords explanationsbiasedbiasesblackboxesclassifierexplanationlime
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

As machine learning black boxes are increasingly being deployed in domains such as healthcare and criminal justice, there is growing emphasis on building tools and techniques for explaining these black boxes in an interpretable manner. Such explanations are being leveraged by domain experts to diagnose systematic errors and underlying biases of black boxes. In this paper, we demonstrate that post hoc explanations techniques that rely on input perturbations, such as LIME and SHAP, are not reliable. Specifically, we propose a novel scaffolding technique that effectively hides the biases of any given classifier by allowing an adversarial entity to craft an arbitrary desired explanation. Our approach can be used to scaffold any biased classifier in such a way that its predictions on the input data distribution still remain biased, but the post hoc explanations of the scaffolded classifier look innocuous. Using extensive evaluation with multiple real-world datasets (including COMPAS), we demonstrate how extremely biased (racist) classifiers crafted by our framework can easily fool popular explanation techniques such as LIME and SHAP into generating innocuous explanations which do not reflect the underlying biases.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Evaluating Model Explanations without Ground Truth

    cs.AI 2025-05 conditional novelty 6.0 of 10

    AXE evaluates local explanations by k-NN predictiveness of top features, requiring neither ground-truth explanations nor model sensitivity.

  2. Enhanced Photonic Chip Design via Interpretable Machine Learning Techniques

    physics.optics 2025-05 conditional novelty 5.0 of 10

    Applying LIME explanations to a CNN classifier of photonic multiplexers shows that connected etched regions favor bandwidth, and a V-shaped initial condition informed by this insight yields all 20 redesigned devices w...

Pith tools