Related papers: Improving Neural Language Modeling via Adversarial…
The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…
The vulnerability of neural network classifiers to adversarial attacks is a major obstacle to their deployment in safety-critical applications. Regularization of network parameters during training can be used to improve adversarial…
Adversarial training (AT) is a regularization method that can be used to improve the robustness of neural network methods by adding small perturbations in the training data. We show how to use AT for the tasks of entity recognition and…
In communication systems, there are many tasks, like modulation recognition, which rely on Deep Neural Networks (DNNs) models. However, these models have been shown to be susceptible to adversarial perturbations, namely imperceptible…
Adversarial training has proven to be effective in hardening networks against adversarial examples. However, the gained robustness is limited by network capacity and number of training samples. Consequently, to build more robust models, it…
Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech…
Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches to training robust models against…
Neuromorphic neural network processors, in the form of compute-in-memory crossbar arrays of memristors, or in the form of subthreshold analog and mixed-signal ASICs, promise enormous advantages in compute density and energy efficiency for…
In this paper, we investigate the following question: Can we obtain adversarially-trained models without training on adversarial examples? Our intuition is that training a model with inherent stochasticity, i.e., optimizing the parameters…
We attribute the vulnerability of natural language processing models to the fact that similar inputs are converted to dissimilar representations in the embedding space, leading to inconsistent outputs, and we propose a novel robust training…
Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations. However, the majority of existing defense methods are tailored to defend against a…
We introduce adaptive input representations for neural language modeling which extend the adaptive softmax of Grave et al. (2017) to input representations of variable capacity. There are several choices on how to factorize the input and…
Recent studies on the adversarial vulnerability of neural networks have shown that models trained with the objective of minimizing an upper bound on the worst-case loss over all possible adversarial perturbations improve robustness against…
Unsupervised word translation from non-parallel inter-lingual corpora has attracted much research interest. Very recently, neural network methods trained with adversarial loss functions achieved high accuracy on this task. Despite the…
The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…
Evaluating on adversarial examples has become a standard procedure to measure robustness of deep learning models. Due to the difficulty of creating white-box adversarial examples for discrete text input, most analyses of the robustness of…
Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…
We present a new approach to encourage neural machine translation to satisfy lexical constraints. Our method acts at the training step and thereby avoiding the introduction of any extra computational overhead at inference step. The proposed…
Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is motivated by equal opportunity, it is not explicitly captured in standard adversarial training. In this paper,…