Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization

Bose, Avishek Joey; Aarabi, Parham

doi:10.48550/arxiv.1805.12302

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, researchers have proposed a large number of white-box attacks [36,27,22,23,37]. For example, Bose et al proposed adversarial attacks on face detectors using neural net based constrained optimization [45]. Yu et al proposed a fast adversarial attack example generation framework based on adversarial saliency prediction [46].…”

Section: White-box Adversarial Attack Modelsmentioning

confidence: 99%

POBA-GA: Perturbation optimized black-box adversarial attacks via genetic algorithm

Chen

Shen

et al. 2019

Computers & Security

View full text Add to dashboard Cite

Most deep learning models are easily vulnerable to adversarial attacks. Various adversarial attacks are designed to evaluate the robustness of models and develop defense model. Currently, adversarial attacks are brought up to attack their own target model with their own evaluation metrics. And most of the black-box adversarial attack algorithms cannot achieve the expected success rate compared with white-box attacks. In this paper,comprehensive evaluation metrics are brought up for different adversarial attack methods. A novel perturbation optimized blackbox adversarial attack based on genetic algorithm (POBA-GA) is proposed for achieving white-box comparable attack performances. Approximate optimal adversarial examples are evolved through evolutionary operations including initialization, selection, crossover and mutation. Fitness function is specifically designed to evaluate the example individual in both aspects of attack ability and perturbation control. Population diversity strategy is brought up in evolutionary process to promise the approximate optimal perturbations obtained. Comprehensive experiments are carried out to testify POBA-GA's performances. Both simulation and application results prove that our method is better than current state-of-art black-box attack methods in aspects of attack capability and perturbation control.

show abstract

Section: White-box Adversarial Attack Modelsmentioning

confidence: 99%

POBA-GA: Perturbation optimized black-box adversarial attacks via genetic algorithm

Chen

Shen

et al. 2019

Computers & Security

View full text Add to dashboard Cite

show abstract

“…Su et al [36] present a method to generate one-pixel adversarial perturbations to attack models using differential evolution in an extremely specific scenario. In the face recognition domain, Bose et al [3] craft adversarial examples by solving constrained optimization so that face detector can not detect faces. Sharif et al [33] propose a method focusing on facial biometric systems which can be widely used in surveillance and access control.…”

Section: Adversarial Attackmentioning

confidence: 99%

Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network

Song¹,

Wu²,

Lü³

2018

Preprint

View full text Add to dashboard Cite

With the broad use of face recognition, its weakness gradually emerges that it is able to be attacked. So, it is important to study how face recognition networks are subject to attacks. In this paper, we focus on a novel way to do attacks against face recognition network that misleads the network to identify someone as the target person not misclassify inconspicuously. Simultaneously, for this purpose, we introduce a specific attentional adversarial attack generative network (A 3 GN ) to generate fake face images. For capturing the semantic information of the target person, this work adds a conditional variational autoencoder and attention modules to learn the instance-level correspondences between faces. Unlike traditional two-player GAN, this work introduces face recognition networks as the third player to participate in the competition between generator and discriminator which allows the attacker to impersonate the target person better. The generated faces which are hard to arouse the notice of onlookers can evade recognition by state-of-the-art networks and most of them are recognized as the target person.

show abstract

Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization

Cited by 2 publications

References 0 publications

POBA-GA: Perturbation optimized black-box adversarial attacks via genetic algorithm

POBA-GA: Perturbation optimized black-box adversarial attacks via genetic algorithm

Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network

Contact Info

Product

Resources

About