Corpus ID: 233481617

Intriguing Usage of Applicability Domain: Lessons from Cheminformatics Applied to Adversarial Learning

@article{Chang2021IntriguingUO,
  title={Intriguing Usage of Applicability Domain: Lessons from Cheminformatics Applied to Adversarial Learning},
  author={Luke Chang and Katharina Dost and Kaiqi Zhao and Ambra Demontis and F. Roli and G. Dobbie and J{\"o}rg Simon Wicker},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.00495}
}
Defending machine learning models from adversarial attacks is still a challenge: none of the “robust” models is utterly immune to adversarial examples to date. Different defences have been proposed; however, most of them are tailored to particular ML models and adversarial attacks, therefore their effectiveness and applicability are strongly limited. A similar problem plagues cheminformatics: Quantitative Structure-Activity Relationship (QSAR) models struggle to predict biological activity for… Expand

References

SHOWING 1-10 OF 37 REFERENCES
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
Towards Deep Learning Models Resistant to Adversarial Attacks
MagNet: A Two-Pronged Defense against Adversarial Examples
Explaining and Harnessing Adversarial Examples
Intriguing properties of neural networks
Adversarial Attacks and Defenses in Deep Learning
Adversarial Examples: Attacks and Defenses for Deep Learning
Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
DeepTest: Automated Testing of Deep-Neural-Network-Driven Autonomous Cars
...
1
2
3
4
...