AdaLoc keeps a model locked to authorized users by confining all post-deployment updates to a chosen subset of weights, preserving both task performance for authorized use and near-random accuracy for unauthorized use across vision and language models.
Explaining and harnessing adversarial examples
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
The paper delivers the first comprehensive systematization of adversarial robustness in QML with new empirical tests showing an accuracy-robustness trade-off, amplitude encoding's vulnerability, and QML's greater susceptibility to evasion attacks than classical models.
The paper formalizes fixed-set worst-case corruption in PBE, implements corruption searches on a string DSL, and shows VPA recovers some margin-1 tasks but fails on public SyGuS where vote margins are near one.
An explainability-aware L0 penalty yields coherent counterfactual edits, and the same geometry defines a Tolerance-Region Confusion Matrix that quantifies class-to-class fragility under interpretable perturbations.
citing papers explorer
-
Re-Key-Free, Risky-Free: Adaptable Model Usage Control
AdaLoc keeps a model locked to authorized users by confining all post-deployment updates to a chosen subset of weights, preserving both task performance for authorized use and near-random accuracy for unauthorized use across vision and language models.
-
SoK: Critical Evaluation of Quantum Machine Learning for Adversarial Robustness
The paper delivers the first comprehensive systematization of adversarial robustness in QML with new empirical tests showing an accuracy-robustness trade-off, amplitude encoding's vulnerability, and QML's greater susceptibility to evasion attacks than classical models.
-
Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery
The paper formalizes fixed-set worst-case corruption in PBE, implements corruption searches on a string DSL, and shows VPA recovers some margin-1 tasks but fails on public SyGuS where vote margins are near one.
-
Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
An explainability-aware L0 penalty yields coherent counterfactual edits, and the same geometry defines a Tolerance-Region Confusion Matrix that quantifies class-to-class fragility under interpretable perturbations.