paper-with-me

홈 › Papers

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 the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs of varying sophistication, the defense-attack arms race has been accelerated. In this paper, we present MODEF, a cross-layer model diversity ensemble framework. MODEF intelligently combines unsupervised model denoising ensemble with supervised model verification ensemble by quantifying model diversity, aiming to boost the robustness of the target model against adversarial examples. Evaluated using eleven representative attacks on popular benchmark datasets, we show that MODEF achieves remarkable defense success rates, compared with existing defense methods, and provides a superior capability of repairing adversarial inputs and making correct predictions with high accuracy in the presence of black-box attacks.

📄 PDF Abstract BibTeX arXiv:1908.07667

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingDiversity

Similar Papers 제목 키워드 기반

Robust Deep Learning Ensemble against Deception

2020-09-14 · Wenqi Wei, Ling Liu

Deep neural network (DNN) models are known to be vulnerable to maliciously crafted adversarial examples and to out-of-distribution inputs drawn sufficiently far away from the training data. How to protect a machine learn…

Adversarial RobustnessDeep LearningDenoisingDiversity+1

Cross-Layer Strategic Ensemble Defense Against Adversarial Examples

2019-10-01 · Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow 외

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 …

Diversity

Verifiable Boosted Tree Ensembles

2024-02-22 · Stefano Calzavara, Lorenzo Cazzaro, Claudio Lucchese, Giulio Ermanno Pibiri

Verifiable learning advocates for training machine learning models amenable to efficient security verification. Prior research demonstrated that specific classes of decision tree ensembles -- called large-spread ensemble…

Generating observation guided ensembles for data assimilation with denoising diffusion probabilistic model

2023-08-13 · Yuuichi Asahi, Yuta Hasegawa, Naoyuki Onodera, Takashi Shimokawabe 외

This paper presents an ensemble data assimilation method using the pseudo ensembles generated by denoising diffusion probabilistic model. Since the model is trained against noisy and sparse observation data, this model c…

Denoising

Verifiable Learning for Robust Tree Ensembles

2023-05-05 · Stefano Calzavara, Lorenzo Cazzaro, Giulio Ermanno Pibiri, Nicola Prezza

Verifying the robustness of machine learning models against evasion attacks at test time is an important research problem. Unfortunately, prior work established that this problem is NP-hard for decision tree ensembles, h…