Add a new attack based on improved Hasofer-Lind, Rackwitz-Fiessler

[p-chaurand]

Implementation of the minimization algorithm iHL-RF ( https://link.springer.com/content/pdf/10.1007/978-0-387-34866-7_32.pdf ) adapted for adversarial attack. This is a minimization attack that work faster and with a lower distortion on (at least) the network efficientnet b0. The predetermined args seems to be the best one to have a fast adversarial example while having a lower distortion than cw or deepfool.

[p-chaurand]

Here are a few comparison between carlini wagner (10*50 steps) , deepfool (100 steps with 10 loss) and iHL-RF attack (50 steps with abort early after 25 steps). These graph has been made with the model efficientnet b0 on 1000 images. The runtime for this attack are the following : 2m10 for iHL-RF, 30m for cw and 3m for deepfool. (with an A100-PCIE-40GB) comparison between cw, deepfool and iHL-RF attacks.pdf

[p-chaurand]

Implementation by Paul Chaurand (ENS Rennes) under the supervision of Teddy Furon (Inria Rennes) of the Hasofer Lind Racwitz Flessler method Rackwitz R., & Flessler B., Structural reliability under combined random load sequences. Computers & Structures, vol. 9, no. 5, pp. 489-494, 1978. Summer 2022