Related papers: Adversarial Sampling and Training for Semi-Supervi…

Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the domain of image processing, recent research shows that speech…

The phenomenon of adversarial examples has been revealed in variant scenarios. Recent studies show that well-designed adversarial defense strategies can improve the robustness of deep learning models against adversarial examples. However,…

We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified…

Tree ensembles are powerful models that are widely used. However, they are susceptible to adversarial examples, which are examples that purposely constructed to elicit a misprediction from the model. This can degrade performance and erode a…

We study an online version of the noisy binary search problem where feedback is generated by a non-stochastic adversary rather than perturbed by random noise. We reframe this as maintaining an accurate estimate for the median of an…

Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high…

Active learning for sentence understanding aims at discovering informative unlabeled data for annotation and therefore reducing the demand for labeled data. We argue that the typical uncertainty sampling method for active learning is…

Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples via an acquisition function. For example, variational adversarial active learning (VAAL) leverages an…

Deep neural networks (DNNs) are powerful nonlinear architectures that are known to be robust to random perturbations of the input. However, these models are vulnerable to adversarial perturbations--small input changes crafted explicitly to…

Generative adversarial nets (GANs) have been widely studied during the recent development of deep learning and unsupervised learning. With an adversarial training mechanism, GAN manages to train a generative model to fit the underlying…

Adversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons still need to be fully understood. In this paper, we identify one cause of overfitting related to current…

Adversarial examples are inputs to a machine learning system that result in an incorrect output from that system. Attacks launched through this type of input can cause severe consequences: for example, in the field of image recognition, a…

When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we…

Adversarial examples can be defined as inputs to a model which induce a mistake - where the model output is different than that of an oracle, perhaps in surprising or malicious ways. Original models of adversarial attacks are primarily…

In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…

Adversarial learning can learn fairer and less biased models of language than standard methods. However, current adversarial techniques only partially mitigate model bias, added to which their training procedures are often unstable. In this…

The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention. Inspired by the success of vision-language foundation models, previous efforts achieved zero-shot adversarial…

State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is an effective approach to defend against such examples. It is formulated as a min-max…

We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the…

The great success of convolutional neural networks has caused a massive spread of the use of such models in a large variety of Computer Vision applications. However, these models are vulnerable to certain inputs, the adversarial examples,…