Related papers: From text to multimodal: a survey of adversarial e…

The introduction of multimodal models is a huge step forward in Artificial Intelligence. A single model is trained to understand multiple modalities: text, image, video, and audio. Open-source multimodal models have made these breakthroughs…

We provide a complete characterisation of the phenomenon of adversarial examples - inputs intentionally crafted to fool machine learning models. We aim to cover all the important concerns in this field of study: (1) the conjectures on the…

Adversarial machine learning is an emerging field that focuses on studying vulnerabilities of machine learning approaches in adversarial settings and developing techniques accordingly to make learning robust to adversarial manipulations. It…

Artificial Intelligence has achieved remarkable success across diverse application domains. However, its vulnerability to adversarial attacks poses significant challenges to reliability, security, and trustworthiness. Adversarial machine…

Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…

Machine learning algorithms are powerful tools for data driven tasks such as image classification and feature detection, however their vulnerability to adversarial examples - input samples manipulated to fool the algorithm - remains a…

Benefiting from large-scale pre-training, we have witnessed significant performance boost on the popular Visual Question Answering (VQA) task. Despite rapid progress, it remains unclear whether these state-of-the-art (SOTA) models are…

Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this…

Recent years have witnessed impressive advances in challenging multi-hop QA tasks. However, these QA models may fail when faced with some disturbance in the input text and their interpretability for conducting multi-hop reasoning remains…

Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of this systems-fathoming how and when neural-based systems fail in such cases is critical…

Contextual question-answering models are susceptible to adversarial perturbations to input context, commonly observed in real-world scenarios. These adversarial noises are designed to degrade the performance of the model by distorting the…

Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible. Research on this problem is still in the…

While a substantial body of prior work has explored adversarial example generation for natural language understanding tasks, these examples are often unrealistic and diverge from the real-world data distributions. In this work, we introduce…

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…

Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on various adversarial…

Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in…

While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved to be useful to…

Question Answering has come a long way from answer sentence selection, relational QA to reading and comprehension. We shift our attention to generative question answering (gQA) by which we facilitate machine to read passages and answer…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…

Learning from multimodal data is an important research topic in machine learning, which has the potential to obtain better representations. In this work, we propose a novel approach to generative modeling of multimodal data based on…