Related papers: Exact Adversarial Attack to Image Captioning via S…
Deep learning is found to be vulnerable to adversarial examples. However, its adversarial susceptibility in image caption generation is under-explored. We study adversarial examples for vision and language models, which typically adopt an…
Recent advances in deep learning research have shown remarkable achievements across many tasks in computer vision (CV) and natural language processing (NLP). At the intersection of CV and NLP is the problem of image captioning, where the…
We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. The problem is both fundamental and interesting, as most machine-generated captions, despite phenomenal…
Visual language grounding is widely studied in modern neural image captioning systems, which typically adopts an encoder-decoder framework consisting of two principal components: a convolutional neural network (CNN) for image feature…
In this paper, we propose a novel conditional-generative-adversarial-nets-based image captioning framework as an extension of traditional reinforcement-learning (RL)-based encoder-decoder architecture. To deal with the inconsistent…
Recently, generative adversarial networks (GAN) have gathered a lot of interest. Their efficiency in generating unseen samples of high quality, especially images, has improved over the years. In the field of Natural Language Generation…
While most image captioning aims to generate objective descriptions of images, the last few years have seen work on generating visually grounded image captions which have a specific style (e.g., incorporating positive or negative…
Automatically generating the descriptions of an image, i.e., image captioning, is an important and fundamental topic in artificial intelligence, which bridges the gap between computer vision and natural language processing. Based on the…
Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafted images that force…
While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the…
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…
We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…
Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…
Deep learning based systems are susceptible to adversarial attacks, where a small, imperceptible change at the input alters the model prediction. However, to date the majority of the approaches to detect these attacks have been designed for…
Adversarial attacks on a convolutional neural network (CNN) -- injecting human-imperceptible perturbations into an input image -- could fool a high-performance CNN into making incorrect predictions. The success of adversarial attacks raises…
With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are…
With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs were…
Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the…
Image captioning models are encoder-decoder architectures trained on large-scale image-text datasets, making them susceptible to adversarial attacks. We present CaptionFool, a novel universal (input-agnostic) adversarial attack against…
Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional…