相关论文: Analyzing Dynamic Adversarial Training Data in the…

In adversarial data collection (ADC), a human workforce interacts with a model in real time, attempting to produce examples that elicit incorrect predictions. Researchers hope that models trained on these more challenging datasets will rely…

In Dynamic Adversarial Data Collection (DADC), human annotators are tasked with finding examples that models struggle to predict correctly. Models trained on DADC-collected training data have been shown to be more robust in adversarial and…

We present our experience as annotators in the creation of high-quality, adversarial machine-reading-comprehension data for extractive QA for Task 1 of the First Workshop on Dynamic Adversarial Data Collection (DADC). DADC is an emergent…

Most previous works usually explained adversarial examples from several specific perspectives, lacking relatively integral comprehension about this problem. In this paper, we present a systematic study on adversarial examples from three…

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution…

Innovations in annotation methodology have been a catalyst for Reading Comprehension (RC) datasets and models. One recent trend to challenge current RC models is to involve a model in the annotation process: humans create questions…

Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial…

Neural networks are susceptible to adversarial examples-small input perturbations that cause models to fail. Adversarial training is one of the solutions that stops adversarial examples; models are exposed to attacks during training and…

We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new dataset leads to state-of-the-art performance on a variety of…

Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have…

Deep neural networks (DNNs) are vulnerable to adversarial examples that are carefully designed to cause the deep learning model to make mistakes. Adversarial examples of 2D images and 3D point clouds have been extensively studied, but…

The pursuit of data efficiency, where quality outweighs quantity, has emerged as a cornerstone in robotic manipulation, especially given the high costs associated with real-world data collection. We propose that maximizing the informational…

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

Neural models of code have shown impressive results when performing tasks such as predicting method names and identifying certain kinds of bugs. We show that these models are vulnerable to adversarial examples, and introduce a novel…

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…

Machine learning researchers have long noticed the phenomenon that the model training process will be more effective and efficient when the training samples are densely sampled around the underlying decision boundary. While this observation…

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…

DL-based automatic modulation classification (AMC) models are highly susceptible to adversarial attacks, where even minimal input perturbations can cause severe misclassifications. While adversarially training an AMC model based on an…

Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective and popular approach, known as…

Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost…