相关论文: Effective and Efficient Adversarial Detection for …

Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…

Data-driven super-resolution (SR) methods are often integrated into imaging pipelines as preprocessing steps to improve downstream tasks such as classification and detection. However, these SR models introduce a previously unexplored attack…

Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content…

Video anomaly detection (VAD) holds immense importance across diverse domains such as surveillance, healthcare, and environmental monitoring. While numerous surveys focus on conventional VAD methods, they often lack depth in exploring…

Learning models capable of providing reliable predictions in the face of adversarial actions has become a central focus of the machine learning community in recent years. This challenge arises from observing that data encountered at…

The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of…

Vision-Language Models (VLMs) extend the capabilities of Large Language Models (LLMs) by incorporating visual information, yet they remain vulnerable to jailbreak attacks, especially when processing noisy or corrupted images. Although…

Addressing hard cases in autonomous driving, such as anomalous road users, extreme weather conditions, and complex traffic interactions, presents significant challenges. To ensure safety, it is crucial to detect and manage these scenarios…

Recently, many studies have demonstrated deep neural network (DNN) classifiers can be fooled by the adversarial example, which is crafted via introducing some perturbations into an original sample. Accordingly, some powerful defense…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…

Deep Learning based AI systems have shown great promise in various domains such as vision, audio, autonomous systems (vehicles, drones), etc. Recent research on neural networks has shown the susceptibility of deep networks to adversarial…

Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…

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…

Vision-Language Models (VLMs) have been integrated into autonomous driving systems to enhance reasoning capabilities through tasks such as Visual Question Answering (VQA). However, the robustness of these systems against backdoor attacks…

Modern self-driving perception systems have been shown to improve upon processing complementary inputs such as LiDAR with images. In isolation, 2D images have been found to be extremely vulnerable to adversarial attacks. Yet, there have…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…

Vision-Language Models (VLMs) have achieved remarkable success in tasks such as image captioning and visual question answering (VQA). However, as their applications become increasingly widespread, recent studies have revealed that VLMs are…

Vision-Language Models (VLMs) have gained considerable prominence in recent years due to their remarkable capability to effectively integrate and process both textual and visual information. This integration has significantly enhanced…

Deep neural networks based object detection models have revolutionized computer vision and fueled the development of a wide range of visual recognition applications. However, recent studies have revealed that deep object detectors can be…

Vision-based perception modules are increasingly deployed in many applications, especially autonomous vehicles and intelligent robots. These modules are being used to acquire information about the surroundings and identify obstacles. Hence,…