paper-with-me

홈 › Papers

Cross-Layer Strategic Ensemble Defense Against Adversarial Examples

2019-10-01 · Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow, Emre Gursoy, Stacey Truex, Yanzhao Wu

Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble framework and a suite of robust defense algorithms, which are attack-independent, and capable of auto-repairing and auto-verifying the target model being attacked. Our strategic ensemble approach makes three original contributions. First, we employ input-transformation diversity to design the input-layer strategic transformation ensemble algorithms. Second, we utilize model-disagreement diversity to develop the output-layer strategic model ensemble algorithms. Finally, we create an input-output cross-layer strategic ensemble defense that strengthens the defensibility by combining diverse input transformation based model ensembles with diverse output verification model ensembles. Evaluated over 10 attacks on ImageNet dataset, we show that our strategic ensemble defense algorithms can achieve high defense success rates and are more robust with high attack prevention success rates and low benign false negative rates, compared to existing representative defense methods.

📄 PDF Abstract BibTeX arXiv:1910.01742

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Ensemble-based Adversarial Defense Using Diversified Distance Mapping

2021-01-01 · Ehsan Kazemi, Mohamed E. Hussein, Wael AbdAlmgaeed

We propose an ensemble-based defense against adversarial examples using distance map layers (DMLs). Similar to linear (map) layers, DMLs can be used to output logits for a multi-class classification model. We show in thi…

Adversarial DefenseDiversityMulti-class Classification

Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks

2019-08-21 · Ka-Ho Chow, Wenqi Wei, Yanzhao Wu, Ling Liu

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to…

DenoisingDiversity

StratDef: Strategic Defense Against Adversarial Attacks in ML-based Malware Detection

2022-02-15 · Aqib Rashid, Jose Such

Over the years, most research towards defenses against adversarial attacks on machine learning models has been in the image recognition domain. The ML-based malware detection domain has received less attention despite it…

Adversarial RobustnessMalware Detection

Run-Off Election: Improved Provable Defense against Data Poisoning Attacks

2023-02-05 · Keivan Rezaei, Kiarash Banihashem, Atoosa Chegini, Soheil Feizi

In data poisoning attacks, an adversary tries to change a model's prediction by adding, modifying, or removing samples in the training data. Recently, ensemble-based approaches for obtaining provable defenses against dat…

Data Poisoning

Ensemble of Models Trained by Key-based Transformed Images for Adversarially Robust Defense Against Black-box Attacks

2020-11-16 · MaungMaung AprilPyone, Hitoshi Kiya

We propose a voting ensemble of models trained by using block-wise transformed images with secret keys for an adversarially robust defense. Key-based adversarial defenses were demonstrated to outperform state-of-the-art …

image-classificationImage Classification