Publication
SafeAMC: Adversarial training for robust modulation classification models
Related publications (47)
Towards Robust Vision Transformer
Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard accuracy and com ...
IEEE COMPUTER SOC2022Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting
Alexandre Massoud Alahi, Parth Ashit Kothari
Human trajectory forecasting in crowds presents the challenges of modelling social interactions and outputting collision-free multimodal distribution. Following the success of Social Generative Adversarial Networks (SGAN), recent works propose various GAN- ...
2022On the benefits of robust models in modulation recognition
Pascal Frossard, Javier Alejandro Maroto Morales
Deep Neural Networks (DNNs) using convolutional layers are state-of-the-art in many tasks in communications. However, in other domains, like image classification, DNNs have been shown to be vulnerable to adversarial perturbations, which consist of impercep ...
2021Predicting optical transmission through complex scattering media from reflection patterns with deep neural networks
Demetri Psaltis, Eirini Kakkava
Deep neural networks (DNNs) are used to reconstruct transmission speckle intensity patterns from the respective reflection speckle intensity patterns generated by illuminated parafilm layers. The dependence of the reconstruction accuracy on the thickness o ...
2021Watermarking-based Defense against Adversarial Attacks on Deep Neural Networks
James Richard Larus, Xiaoting Li, Dinghao Wu, Junjun Zhang
The vulnerability of deep neural networks to adversarial attacks has posed significant threats to real-world applications, especially security-critical ones. Given a well-trained model, slight modifications to the input samples can cause drastic changes in ...
IEEE2021Biologically plausible unsupervised learning in shallow and deep neural networks
The way our brain learns to disentangle complex signals into unambiguous concepts is fascinating but remains largely unknown. There is evidence, however, that hierarchical neural representations play a key role in the cortex. This thesis investigates biolo ...
EPFL2021Robustness via Cross-Domain Ensembles
Shuqing Teresa Yeo, Amir Roshan Zamir, Oguzhan Fatih Kar
We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong predi ...
IEEE2021Generating Smooth Pose Sequences for Diverse Human Motion Prediction
Recent progress in stochastic motion prediction, i.e., predicting multiple possible future human motions given a single past pose sequence, has led to producing truly diverse future motions and even providing control over the motion of some body parts. How ...
IEEE2021Supplementary Material - AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks
Sabine Süsstrunk, Majed El Helou, Frederike Dümbgen
In this supplementary material, we present the details of the neural network architecture and training settings used in all our experiments. This holds for all experiments presented in the main paper as well as in this supplementary material. We also show ...
2020Disentangling feature and lazy training in deep neural networks
Matthieu Wyart, Mario Geiger, Stefano Spigler, Arthur Jacot
Two distinct limits for deep learning have been derived as the network width h -> infinity, depending on how the weights of the last layer scale with h. In the neural tangent Kernel (NTK) limit, the dynamics becomes linear in the weights and is described b ...
IOP PUBLISHING LTD2020