paper-with-me

Papers

Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm

2023-03-28 · Bakary Badjie, José Cecílio, António Casimiro

Adversarial attacks significantly threaten the robustness of deep neural networks (DNNs). Despite the multiple defensive methods employed, they are nevertheless vulnerable to poison attacks, where attackers meddle with the initial training data. In order to defend DNNs against such adversarial attacks, this work proposes a novel method that combines the defensive distillation mechanism with a denoising autoencoder (DAE). This technique tries to lower the sensitivity of the distilled model to poison attacks by spotting and reconstructing poisonous adversarial inputs in the training data. We added carefully created adversarial samples to the initial training data to assess the proposed method's performance. Our experimental findings demonstrate that our method successfully identified and reconstructed the poisonous inputs while also considering enhancing the DNN's resilience. The proposed approach provides a potent and robust defense mechanism for DNNs in various applications where data poisoning attacks are a concern. Thus, the defensive distillation technique's limitation posed by poisonous adversarial attacks is overcome.

📄 PDF Abstract BibTeX arXiv:2303.15901

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessData PoisoningDenoising

Methods 이 논문이 사용한 방법론

Denoising Autoencoder A Denoising Autoencoder is a modification on the autoencoder to prevent the network learning the identity function.…

Similar Papers 제목 키워드 기반

Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples

2019-08-21 · Marcus Soll, Tobias Hinz, Sven Magg, Stefan Wermter

Adversarial examples are artificially modified input samples which lead to misclassifications, while not being detectable by humans. These adversarial examples are a challenge for many tasks such as image and text classi…

Adversarial TextClassificationGeneral Classificationimage-classification+3

Improving Defensive Distillation using Teacher Assistant

2023-05-14 · Maniratnam Mandal, Suna Gao

Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications. More specifically, in computer vision-based tasks, experts can use the knowledge of m…

Face RecognitionKnowledge DistillationSelf-Driving Cars

Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks

2015-11-14 · Nicolas Papernot, Patrick McDaniel, Xi Wu, Somesh Jha 외

Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems. However, recent studies have shown that deep learning, like other machine learning techniques, is vulnerable…

Autonomous VehiclesBIG-bench Machine Learning

SEDA: Self-Ensembling ViT with Defensive Distillation and Adversarial Training for robust Chest X-rays Classification

2023-08-15 · Raza Imam, Ibrahim Almakky, Salma Alrashdi, Baketah Alrashdi 외

Deep Learning methods have recently seen increased adoption in medical imaging applications. However, elevated vulnerabilities have been explored in recent Deep Learning solutions, which can hinder future adoption. Parti…

Computational EfficiencyX-ray Classification

Towards Evaluating the Robustness of Neural Networks

2016-08-16 · Nicholas Carlini, David Wagner

Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input $x$ and any target classification $t$, it is possibl…

Adversarial Attack