Morphence: Moving Target Defense Against Adversarial Examples
Robustness to adversarial examples of machine learning models remains an open topic of research. Attacks often succeed by repeatedly probing a fixed target model with adversarial examples purposely crafted to fool it. In this paper, we introduce Morphence, an approach that shifts the defense landscape by making a model a moving target against adversarial examples. By regularly moving the decision function of a model, Morphence makes it significantly challenging for repeated or correlated attacks to succeed. Morphence deploys a pool of models generated from a base model in a manner that introduces sufficient randomness when it responds to prediction queries. To ensure repeated or correlated attacks fail, the deployed pool of models automatically expires after a query budget is reached and the model pool is seamlessly replaced by a new model pool generated in advance. We evaluate Morphence on two benchmark image classification datasets (MNIST and CIFAR10) against five reference attacks (2 white-box and 3 black-box). In all cases, Morphence consistently outperforms the thus-far effective defense, adversarial training, even in the face of strong white-box attacks, while preserving accuracy on clean data.
Code (1)
Tasks
image-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution Detection
Evasion attacks against machine learning models often succeed via iterative probing of a fixed target model, whereby an attack that succeeds once will succeed repeatedly. One promising approach to counter this threat is …
image-classificationImage ClassificationOut-of-Distribution DetectionOut of Distribution (OOD) Detection+1MorphStrata: Layer-Specific Perturbations for Generating Morphence Students in Time-Series Moving Target Defense
Time-series forecasting models remain vulnerable to gradient-based adversarial attacks while existing defense mechanisms typically incur a trade-off in robustness for bounded response and compute cost. The problem is pro…
Adversarial RobustnessMTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense
Present attack methods can make state-of-the-art classification systems based on deep neural networks misclassify every adversarially modified test example. The design of general defense strategies against a wide range o…
ClassificationGeneral ClassificationEffectiveness of Moving Target Defenses for Adversarial Attacks in ML-based Malware Detection
Several moving target defenses (MTDs) to counter adversarial ML attacks have been proposed in recent years. MTDs claim to increase the difficulty for the attacker in conducting attacks by regularly changing certain eleme…
Malware DetectionMoving Target Defense for Deep Visual Sensing against Adversarial Examples
Deep learning based visual sensing has achieved attractive accuracy but is shown vulnerable to adversarial example attacks. Specifically, once the attackers obtain the deep model, they can construct adversarial examples …
GPU