CARBEN: Composite Adversarial Robustness Benchmark

07/16/2022
by   Lei Hsiung, et al.
ibm
National Tsing Hua University
Columbia University
0

Prior literature on adversarial attack methods has mainly focused on attacking with and defending against a single threat model, e.g., perturbations bounded in Lp ball. However, multiple threat models can be combined into composite perturbations. One such approach, composite adversarial attack (CAA), not only expands the perturbable space of the image, but also may be overlooked by current modes of robustness evaluation. This paper demonstrates how CAA's attack order affects the resulting image, and provides real-time inferences of different models, which will facilitate users' configuration of the parameters of the attack level and their rapid evaluation of model prediction. A leaderboard to benchmark adversarial robustness against CAA is also introduced.

READ FULL TEXT

page 1

page 2

02/09/2022

Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations

Model robustness against adversarial examples of single perturbation typ...
03/01/2021

Mind the box: l_1-APGD for sparse adversarial attacks on image classifiers

We show that when taking into account also the image domain [0,1]^d, est...
05/31/2020

Evaluations and Methods for Explanation through Robustness Analysis

Among multiple ways of interpreting a machine learning model, measuring ...
07/13/2023

Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations

Deep neural networks have proven to be vulnerable to adversarial attacks...
05/31/2021

Robustifying ℓ_∞ Adversarial Training to the Union of Perturbation Models

Classical adversarial training (AT) frameworks are designed to achieve h...
04/26/2020

Improved Image Wasserstein Attacks and Defenses

Robustness against image perturbations bounded by a ℓ_p ball have been w...
03/02/2022

Canonical foliations of neural networks: application to robustness

Adversarial attack is an emerging threat to the trustability of machine ...

Please sign up or login with your details

Forgot password? Click here to reset