Related papers: Iterative Adversarial Attack on Image-guided Story…
Cross-modal audio-visual perception has been a long-lasting topic in psychology and neurology, and various studies have discovered strong correlations in human perception of auditory and visual stimuli. Despite works in computational…
The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly…
Multimodal Machine Learning systems, particularly those aligning text and image data like CLIP/BLIP models, have become increasingly prevalent, yet remain susceptible to adversarial attacks. While substantial research has addressed…
Multimodal retrieval-augmented generation (RAG) enhances the visual reasoning capability of vision-language models (VLMs) by dynamically accessing information from external knowledge bases. In this work, we introduce \textit{Poisoned-MRAG},…
Adversarial attacks provide a good way to study the robustness of deep learning models. One category of methods in transfer-based black-box attack utilizes several image transformation operations to improve the transferability of…
We are interested in learning visual representations which allow for 3D manipulations of visual objects based on a single 2D image. We cast this into an image-to-image transformation task, and propose Iterative Generative Adversarial…
Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…
Smart healthcare systems are gaining popularity with the rapid development of intelligent sensors, the Internet of Things (IoT) applications and services, and wireless communications. However, at the same time, several vulnerabilities and…
Multi-modal embeddings encode texts, images, thermal images, sounds, and videos into a single embedding space, aligning representations across different modalities (e.g., associate an image of a dog with a barking sound). In this paper, we…
We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model…
Targeted adversarial attacks are widely used to evaluate the robustness of neural machine translation systems. Unfortunately, this paper first identifies a critical issue in the existing settings of NMT targeted adversarial attacks, where…
Compared to single-target adversarial attacks, multi-target attacks have garnered significant attention due to their ability to generate adversarial images for multiple target classes simultaneously. However, existing generative approaches…
Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification.For text classification, however, existing synonym substitution based adversarial attacks are…
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…
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…
Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters…
Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain considerable similarity to…
Neural conversational models learn to generate responses by taking into account the dialog history. These models are typically optimized over the query-response pairs with a maximum likelihood estimation objective. However, the…
Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models…
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…