Related papers: Efficient and Effective Universal Adversarial Atta…

Large vision-language models (VLMs) have advanced multimodal tasks such as video question answering (QA). However, VLMs face the challenge of selecting frames effectively and efficiently, as standard uniform sampling is expensive and…

Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels.…

Despite the excellent performance of vision-language pre-trained models (VLPs) on conventional VQA task, they still suffer from two problems: First, VLPs tend to rely on language biases in datasets and fail to generalize to…

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

Despite modifying only a small localized input region, adversarial patches can drastically change the prediction of computer vision models. However, prior methods either cannot perform satisfactorily under targeted attack scenarios or fail…

Deep hash-based retrieval techniques are widely used in facial retrieval systems to improve the efficiency of facial matching. However, it also carries the danger of exposing private information. Deep hash models are easily influenced by…

In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream…

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock…

Adversarial attacks in visual object tracking have significantly degraded the performance of advanced trackers by introducing imperceptible perturbations into images. However, there is still a lack of research on designing adversarial…

Deep Neural Networks (DNNs) are vulnerable to adversarial examples generated by imposing subtle perturbations to inputs that lead a model to predict incorrect outputs. Currently, a large number of researches on defending adversarial…

3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks. However, their adversarial robustness remains largely unexplored. Prior work in 2D VLMs…

Recent works have illustrated that modern NLP models trained for diverse tasks ranging from sentiment analysis to language generation succumb to universal adversarial attacks, a class of input-agnostic attacks where a common trigger…

Although deep learning has made remarkable progress in processing various types of data such as images, text and speech, they are known to be susceptible to adversarial perturbations: perturbations specifically designed and added to the…

Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the digital setting, leaving physical-world threats largely…

Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve frequent queries to the target model or rely on surrogate models closely mirroring the target model…

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce misclassification in a large fraction of images of a specific class. Unlike previous methods…

Deep learning has achieved remarkable success in direction-of-arrival (DOA) estimation. However, recent studies have shown that adversarial perturbations can severely compromise the performance of such models. To address this vulnerability,…

Object detection systems using deep learning models have become increasingly popular in robotics thanks to the rising power of CPUs and GPUs in embedded systems. However, these models are susceptible to adversarial attacks. While some…

In recent years, NLP practitioners have converged on the following practice: (i) import an off-the-shelf pretrained (masked) language model; (ii) append a multilayer perceptron atop the CLS token's hidden representation (with randomly…

Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack…