Related papers: CaptionFool: Universal Image Captioning Model Atta…
We propose an end-to-end model which generates captions for images embedded in news articles. News images present two key challenges: they rely on real-world knowledge, especially about named entities; and they typically have linguistically…
We show that we can easily design a single adversarial perturbation $P$ that changes the class of $n$ images $X_1,X_2,\dots,X_n$ from their original, unperturbed classes $c_1, c_2,\dots,c_n$ to desired (not necessarily all the same) classes…
Deep learning models are known to be vulnerable not only to input-dependent adversarial attacks but also to input-agnostic or universal adversarial attacks. Dezfooli et al. \cite{Dezfooli17,Dezfooli17anal} construct universal adversarial…
Image Captioning is a task that combines computer vision and natural language processing, where it aims to generate descriptive legends for images. It is a two-fold process relying on accurate image understanding and correct language…
Unrestricted color attacks, which manipulate semantically meaningful color of an image, have shown their stealthiness and success in fooling both human eyes and deep neural networks. However, current works usually sacrifice the flexibility…
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…
State-of-the-art image captioners can generate accurate sentences to describe images in a sequence to sequence manner without considering the controllability and interpretability. This, however, is far from making image captioning widely…
The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…
Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial…
Image captioning involves generating textual descriptions from input images, bridging the gap between computer vision and natural language processing. Recent advancements in transformer-based models have significantly improved caption…
Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image…
Recent research has revealed that the output of Deep Neural Networks (DNN) can be easily altered by adding relatively small perturbations to the input vector. In this paper, we analyze an attack in an extremely limited scenario where only…
Automated content filtering and moderation is an important tool that allows online platforms to build striving user communities that facilitate cooperation and prevent abuse. Unfortunately, resourceful actors try to bypass automated filters…
Video recognition systems are vulnerable to adversarial examples. Recent studies show that style transfer-based and patch-based unrestricted perturbations can effectively improve attack efficiency. These attacks, however, face two main…
In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for…
Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly…
This work examines the vulnerability of multimodal (image + text) models to adversarial threats similar to those discussed in previous literature on unimodal (image- or text-only) models. We introduce realistic assumptions of partial model…
Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder-decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to be…
Most image captioning frameworks generate captions directly from images, learning a mapping from visual features to natural language. However, editing existing captions can be easier than generating new ones from scratch. Intuitively, when…
Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the…