Skip to Main content Skip to Navigation
Journal articles

Probabilistic Jacobian-Based Saliency Maps Attacks

Abstract : This paper introduces simple, faster and more efficient versions of the known targeted and untargeted Jacobian-based Saliency Map Attacks (JSMA). Despite creating adversarial examples with a higher average L 0 distance than the state-of-the-art Carlini-Wagner attack, the new versions of JSMA have a significant speed advantage over this attack, making them very convenient for L 0 real-time robustness testing of neural network classifiers.
Document type :
Journal articles
Complete list of metadata
Contributor : Hatem Hajri Connect in order to contact the contributor
Submitted on : Tuesday, December 22, 2020 - 9:40:53 AM
Last modification on : Wednesday, December 23, 2020 - 11:01:06 AM

Links full text



Théo Combey, António Loison, Maxime Faucher, Hatem Hajri. Probabilistic Jacobian-Based Saliency Maps Attacks. Machine Learning and Knowledge Extraction, MDPI, 2020, 2 (4), pp.558 - 578. ⟨10.3390/make2040030⟩. ⟨hal-03085884⟩



Record views