Related papers: Not What You Asked For: Typographic Attacks in Hou…
Robots navigating indoor environments often have access to architectural plans, which can serve as prior knowledge to enhance their localization and mapping capabilities. While some SLAM algorithms leverage these plans for global…
Autonomous robots require change-robust spatial-semantic reasoning: using spatial and semantic knowledge to decide where to go, how to get there, and where the robot is despite environmental change. Existing approaches typically attach…
The security issue of mobile robots has attracted considerable attention in recent years. In this paper, we propose an intelligent physical attack to trap mobile robots into a preset position by learning the obstacle-avoidance mechanism…
Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on…
Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images…
Robotic grasping faces new challenges in human-robot-interaction scenarios. We consider the task that the robot grasps a target object designated by human's language directives. The robot not only needs to locate a target based on…
Non-rigid 3D mesh matching is a critical step in computer vision and computer graphics pipelines. We tackle matching meshes that contain topological artefacts which can break the assumption made by current approaches. While Functional Maps…
Physical attacks form one of the most severe threats against secure computing platforms. Their criticality arises from their corresponding threat model: By, e.g., passively measuring an integrated circuit's (IC's) environment during a…
Conventional navigation pipelines for legged robots remain largely geometry-centric, relying on dense SLAM representations that are fragile under rapid motion and offer limited support for semantic decision making in open-world exploration.…
The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to…
Accurate localization is a fundamental requirement for autonomous robots operating in indoor environments. Scene graphs encode the spatial structure of an environment as a hierarchy of semantic entities and their relationships, and can be…
Stereotypes, bias, and discrimination have been extensively documented in Machine Learning (ML) methods such as Computer Vision (CV) [18, 80], Natural Language Processing (NLP) [6], or both, in the case of large image and caption models…
The human language is one of the most natural interfaces for humans to interact with robots. This paper presents a robot system that retrieves everyday objects with unconstrained natural language descriptions. A core issue for the system is…
A metric-accurate semantic 3D representation is essential for many robotic tasks. This work proposes a simple, yet powerful, way to integrate the 2D embeddings of a Vision-Language Model in a metric-accurate 3D representation at real-time.…
Despite great strides in language-guided manipulation, existing work has been constrained to table-top settings. Table-tops allow for perfect and consistent camera angles, properties are that do not hold in mobile manipulation. Task plans…
Intelligent embodied agents (e.g. robots) need to perform complex semantic tasks in unfamiliar environments. Among many skills that the agents need to possess, building and maintaining a semantic map of the environment is most crucial in…
Does progress in simulation translate to progress on robots? If one method outperforms another in simulation, how likely is that trend to hold in reality on a robot? We examine this question for embodied PointGoal navigation, developing…
Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with a downstream-oriented…
This paper investigates a novel algorithmic vulnerability when imperceptible image layers confound multiple vision models into arbitrary label assignments and captions. We explore image preprocessing methods to introduce stealth…
Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the training…