SurFree: a fast surrogate-free black-box attack

by   Thibault Maho, et al.

Machine learning classifiers are critically prone to evasion attacks. Adversarial examples are slightly modified inputs that are then misclassified, while remaining perceptively close to their originals. Last couple of years have witnessed a striking decrease in the amount of queries a black box attack submits to the target classifier, in order to forge adversarials. This particularly concerns the black-box score-based setup, where the attacker has access to top predicted probabilites: the amount of queries went from to millions of to less than a thousand. This paper presents SurFree, a geometrical approach that achieves a similar drastic reduction in the amount of queries in the hardest setup: black box decision-based attacks (only the top-1 label is available). We first highlight that the most recent attacks in that setup, HSJA, QEBA and GeoDA all perform costly gradient surrogate estimations. SurFree proposes to bypass these, by instead focusing on careful trials along diverse directions, guided by precise indications of geometrical properties of the classifier decision boundaries. We motivate this geometric approach before performing a head-to-head comparison with previous attacks with the amount of queries as a first class citizen. We exhibit a faster distortion decay under low query amounts (few hundreds to a thousand), while remaining competitive at higher query budgets.



There are no comments yet.


page 8


Black-box Adversarial Attacks with Limited Queries and Information

Current neural network-based classifiers are susceptible to adversarial ...

AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks

Recent studies have shown that adversarial examples in state-of-the-art ...

Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization

Solving for adversarial examples with projected gradient descent has bee...

Explain2Attack: Text Adversarial Attacks via Cross-Domain Interpretability

Training robust deep learning models for down-stream tasks is a critical...

Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks

The field of adversarial machine learning has experienced a near exponen...

Darker than Black-Box: Face Reconstruction from Similarity Queries

Several methods for inversion of face recognition models were recently p...

Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks

We consider adversarial examples in the black-box decision-based scenari...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.