Filtreler

2022 - 20242
Filtreleri Sıfırla

Ayarlar

search.filters.applied.f.publicationcategory: Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı × Konu: Activation functions ×

Arama Sonuçları

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Yayın
    Unreasonable effectiveness of last hidden layer activations for adversarial robustness
    (Institute of Electrical and Electronics Engineers Inc., 2022) Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa Taner
    In standard Deep Neural Network (DNN) based classifiers, the general convention is to omit the activation function in the last (output) layer and directly apply the softmax function on the logits to get the probability scores of each class. In this type of architectures, the loss value of the classifier against any output class is directly proportional to the difference between the final probability score and the label value of the associated class. Standard White-box adversarial evasion attacks, whether targeted or untargeted, mainly try to exploit the gradient of the model loss function to craft adversarial samples and fool the model. In this study, we show both mathematically and experimentally that using some widely known activation functions in the output layer of the model with high temperature values has the effect of zeroing out the gradients for both targeted and untargeted attack cases, preventing attackers from exploiting the model's loss function to craft adversarial samples. We've experimentally verified the efficacy of our approach on MNIST (Digit), CIFAR10 datasets. Detailed experiments confirmed that our approach substantially improves robustness against gradient-based targeted and untargeted attack threats. And, we showed that the increased non-linearity at the output layer has some ad-ditional benefits against some other attack methods like Deepfool attack.
  • Küçük Resim
    Yayın
    Efficient estimation of Sigmoid and Tanh activation functions for homomorphically encrypted data using Artificial Neural Networks
    (Institute of Electrical and Electronics Engineers Inc., 2024) Harb, Mhd Raja Abou; Çeliktaş, Barış
    This paper presents a novel approach to estimating Sigmoid and Tanh activation functions using Artificial Neural Networks (ANN) optimized for homomorphic encryption. The proposed method is compared against second-degree polynomial and Piecewise Linear approximations, demonstrating a minor loss in accuracy while maintaining computational efficiency. Our results suggest that the ANN-based estimator is a viable alternative for secure machine learning models requiring privacypreserving computation.