相关论文: Attacking the Loop: Adversarial Attacks on Graph-b…

Loop Closure Detection (LCD) is the essential module in the simultaneous localization and mapping (SLAM) task. In the current appearance-based SLAM methods, the visual inputs are usually affected by illumination, appearance and viewpoints…

In Simultaneous Localization and Mapping (SLAM), Loop Closure Detection (LCD) is essential to minimize drift when recognizing previously visited places. Visual Bag-of-Words (vBoW) has been an LCD algorithm of choice for many…

Stable feature extraction is the key for the Loop closure detection (LCD) task in the simultaneously localization and mapping (SLAM) framework. In our paper, the feature extraction is operated by using a generative adversarial networks…

Loop closure is necessary for correcting errors accumulated in simultaneous localization and mapping (SLAM) in unknown environments. However, conventional loop closure methods based on low-level geometric or image features may cause high…

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…

Loop-closure detection (LCD) in large non-stationary environments remains an important challenge in robotic visual simultaneous localization and mapping (vSLAM). To reduce computational and perceptual complexity, it is helpful if a vSLAM…

Loop closure detection (LCD) is an indispensable part of simultaneous localization and mapping systems (SLAM); it enables robots to produce a consistent map by recognizing previously visited places. When robots operate over extended…

Loop Closure Detection (LCD) is an essential component of visual simultaneous localization and mapping (SLAM) systems. It enables the recognition of previously visited scenes to eliminate pose and map estimate drifts arising from long-term…

Continuous advancements in deep learning have led to significant progress in feature detection, resulting in enhanced accuracy in tasks like Simultaneous Localization and Mapping (SLAM). Nevertheless, the vulnerability of deep neural…

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt…

Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new…

Stand-alone Visual Place Recognition (VPR) systems have little defence against a well-designed adversarial attack, which can lead to disastrous consequences when deployed for robot navigation. This paper extensively analyzes the effect of…

Loop closure detection (LCD) is a core component of simultaneous localization and mapping (SLAM): it identifies revisited places and enables pose-graph constraints that correct accumulated drift. Classic bag-of-words approaches such as DBoW…

Loop closure detection (LCD) is the key module in appearance based simultaneously localization and mapping (SLAM). However, in the real life, the appearance of visual inputs are usually affected by the illumination changes and texture…

Graph contrastive learning is the state-of-the-art unsupervised graph representation learning framework and has shown comparable performance with supervised approaches. However, evaluating whether the graph contrastive learning is robust to…

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities; however, these models remain highly susceptible to adversarial attacks. While existing research has explored white-box…

Graph adversarial attacks are usually produced from the two perspectives of topology/structure and node feature, both of them represent the paramount characteristics learned by today's deep learning models. Although some defense…

Adversarial attacks expose a fundamental vulnerability in modern deep vision models by exploiting their dependence on dense, pixel-level representations that are highly sensitive to imperceptible perturbations. Traditional defense…

Large Language Models (LLMs) are increasingly integrated with graph-structured data for tasks like node classification, a domain traditionally dominated by Graph Neural Networks (GNNs). While this integration leverages rich relational…

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While existing research has primarily focused on…