Itay Naeh

Meir Brand, Itay Naeh, Daniel Teitelman

In this paper, we present a proof of concept for adversarially attacking the image-based localization module of an autonomous vehicle. This attack aims to cause the vehicle to perform a wrong navigational decisions and prevent it from reaching a desired predefined destination in a simulated urban environment. A database of rendered images allowed us to train a deep neural network that performs a localization task and implement, develop and assess the adversarial pattern. Our tests show that using this adversarial attack we can prevent the vehicle from turning at a given intersection. This is done by manipulating the vehicle's navigational module to falsely estimate its current position and thus fail to initialize the turning procedure until the vehicle misses the last opportunity to perform a safe turn in a given intersection.

Adir Rahamim, Itay Naeh

In this paper, we introduce a novel neural network training framework that increases model's adversarial robustness to adversarial attacks while maintaining high clean accuracy by combining contrastive learning (CL) with adversarial training (AT). We propose to improve model robustness to adversarial attacks by learning feature representations that are consistent under both data augmentations and adversarial perturbations. We leverage contrastive learning to improve adversarial robustness by considering an adversarial example as another positive example, and aim to maximize the similarity between random augmentations of data samples and their adversarial example, while constantly updating the classification head in order to avoid a cognitive dissociation between the classification head and the embedding space. This dissociation is caused by the fact that CL updates the network up to the embedding space, while freezing the classification head which is used to generate new positive adversarial examples. We validate our method, Contrastive Learning with Adversarial Features(CLAF), on the CIFAR-10 dataset on which it outperforms both robust accuracy and clean accuracy over alternative supervised and self-supervised adversarial learning methods.

Daniel Teitelman, Itay Naeh, Shie Mannor

This paper makes a substantial step towards cloning the functionality of black-box models by introducing a Machine learning (ML) architecture named Deep Neural Trees (DNTs). This new architecture can learn to separate different tasks of the black-box model, and clone its task-specific behavior. We propose to train the DNT using an active learning algorithm to obtain faster and more sample-efficient training. In contrast to prior work, we study a complex "victim" black-box model based solely on input-output interactions, while at the same time the attacker and the victim model may have completely different internal architectures. The attacker is a ML based algorithm whereas the victim is a generally unknown module, such as a multi-purpose digital chip, complex analog circuit, mechanical system, software logic or a hybrid of these. The trained DNT module not only can function as the attacked module, but also provides some level of explainability to the cloned model due to the tree-like nature of the proposed architecture.

Roi Pony, Itay Naeh, Shie Mannor

Deep neural networks for video classification, just like image classification networks, may be subjected to adversarial manipulation. The main difference between image classifiers and video classifiers is that the latter usually use temporal information contained within the video. In this work we present a manipulation scheme for fooling video classifiers by introducing a flickering temporal perturbation that in some cases may be unnoticeable by human observers and is implementable in the real world. After demonstrating the manipulation of action classification of single videos, we generalize the procedure to make universal adversarial perturbation, achieving high fooling ratio. In addition, we generalize the universal perturbation and produce a temporal-invariant perturbation, which can be applied to the video without synchronizing the perturbation to the input. The attack was implemented on several target models and the transferability of the attack was demonstrated. These properties allow us to bridge the gap between simulated environment and real-world application, as will be demonstrated in this paper for the first time for an over-the-air flickering attack.