Multi-objective Search of Robust Neural Architectures against Multiple
Types of Adversarial Attacks
- URL: http://arxiv.org/abs/2101.06507v1
- Date: Sat, 16 Jan 2021 19:38:16 GMT
- Title: Multi-objective Search of Robust Neural Architectures against Multiple
Types of Adversarial Attacks
- Authors: Jia Liu and Yaochu Jin
- Abstract summary: deep learning models are vulnerable to adversarial examples that are imperceptible to humans.
It is practically impossible to predict beforehand which type of attacks a machine learn model may suffer from.
We propose to search for deep neural architectures that are robust to five types of well-known adversarial attacks using a multi-objective evolutionary algorithm.
- Score: 18.681859032630374
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Many existing deep learning models are vulnerable to adversarial examples
that are imperceptible to humans. To address this issue, various methods have
been proposed to design network architectures that are robust to one particular
type of adversarial attacks. It is practically impossible, however, to predict
beforehand which type of attacks a machine learn model may suffer from. To
address this challenge, we propose to search for deep neural architectures that
are robust to five types of well-known adversarial attacks using a
multi-objective evolutionary algorithm. To reduce the computational cost, a
normalized error rate of a randomly chosen attack is calculated as the
robustness for each newly generated neural architecture at each generation. All
non-dominated network architectures obtained by the proposed method are then
fully trained against randomly chosen adversarial attacks and tested on two
widely used datasets. Our experimental results demonstrate the superiority of
optimized neural architectures found by the proposed approach over
state-of-the-art networks that are widely used in the literature in terms of
the classification accuracy under different adversarial attacks.
Related papers
- Sparse and Transferable Universal Singular Vectors Attack [5.498495800909073]
We propose a novel sparse universal white-box adversarial attack.
Our approach is based on truncated power providing sparsity to $(p,q)$-singular vectors of the hidden layers of Jacobian matrices.
Our findings demonstrate the vulnerability of state-of-the-art models to sparse attacks and highlight the importance of developing robust machine learning systems.
arXiv Detail & Related papers (2024-01-25T09:21:29Z) - Deviations in Representations Induced by Adversarial Attacks [0.0]
Research has shown that deep learning models are vulnerable to adversarial attacks.
This finding brought about a new direction in research, whereby algorithms were developed to attack and defend vulnerable networks.
We present a method for measuring and analyzing the deviations in representations induced by adversarial attacks.
arXiv Detail & Related papers (2022-11-07T17:40:08Z) - A Multi-objective Memetic Algorithm for Auto Adversarial Attack
Optimization Design [1.9100854225243937]
Well-designed adversarial defense strategies can improve the robustness of deep learning models against adversarial examples.
Given the defensed model, the efficient adversarial attack with less computational burden and lower robust accuracy is needed to be further exploited.
We propose a multi-objective memetic algorithm for auto adversarial attack optimization design, which realizes the automatical search for the near-optimal adversarial attack towards defensed models.
arXiv Detail & Related papers (2022-08-15T03:03:05Z) - Improving robustness of jet tagging algorithms with adversarial training [56.79800815519762]
We investigate the vulnerability of flavor tagging algorithms via application of adversarial attacks.
We present an adversarial training strategy that mitigates the impact of such simulated attacks.
arXiv Detail & Related papers (2022-03-25T19:57:19Z) - Robust Binary Models by Pruning Randomly-initialized Networks [57.03100916030444]
We propose ways to obtain robust models against adversarial attacks from randomly-d binary networks.
We learn the structure of the robust model by pruning a randomly-d binary network.
Our method confirms the strong lottery ticket hypothesis in the presence of adversarial attacks.
arXiv Detail & Related papers (2022-02-03T00:05:08Z) - Meta Adversarial Perturbations [66.43754467275967]
We show the existence of a meta adversarial perturbation (MAP)
MAP causes natural images to be misclassified with high probability after being updated through only a one-step gradient ascent update.
We show that these perturbations are not only image-agnostic, but also model-agnostic, as a single perturbation generalizes well across unseen data points and different neural network architectures.
arXiv Detail & Related papers (2021-11-19T16:01:45Z) - Automated Decision-based Adversarial Attacks [48.01183253407982]
We consider the practical and challenging decision-based black-box adversarial setting.
Under this setting, the attacker can only acquire the final classification labels by querying the target model.
We propose to automatically discover decision-based adversarial attack algorithms.
arXiv Detail & Related papers (2021-05-09T13:15:10Z) - Explainable Adversarial Attacks in Deep Neural Networks Using Activation
Profiles [69.9674326582747]
This paper presents a visual framework to investigate neural network models subjected to adversarial examples.
We show how observing these elements can quickly pinpoint exploited areas in a model.
arXiv Detail & Related papers (2021-03-18T13:04:21Z) - Increasing the Confidence of Deep Neural Networks by Coverage Analysis [71.57324258813674]
This paper presents a lightweight monitoring architecture based on coverage paradigms to enhance the model against different unsafe inputs.
Experimental results show that the proposed approach is effective in detecting both powerful adversarial examples and out-of-distribution inputs.
arXiv Detail & Related papers (2021-01-28T16:38:26Z) - Architectural Resilience to Foreground-and-Background Adversarial Noise [0.0]
Adrial attacks in the form of imperceptible perturbations of normal images have been extensively studied.
We propose distinct model-agnostic benchmark perturbations of images to investigate resilience and robustness of different network architectures.
arXiv Detail & Related papers (2020-03-23T01:38:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.