相关论文: Defending Object Detectors against Patch Attacks w…

Adversarial patch-based attacks aim to fool a neural network with an intentionally generated noise, which is concentrated in a particular region of an input image. In this work, we perform an in-depth analysis of different patch generation…

Automated driving systems rely on 3D object detectors to recognize possible obstacles from LiDAR point clouds. However, recent works show the adversary can forge non-existent cars in the prediction results with a few fake points (i.e.,…

Machine learning is increasingly critical for analysis of the ever-growing corpora of overhead imagery. Advanced computer vision object detection techniques have demonstrated great success in identifying objects of interest such as ships,…

The adversarial patch attack against image classification models aims to inject adversarially crafted pixels within a restricted image region (i.e., a patch) for inducing model misclassification. This attack can be realized in the physical…

An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "patch" fashion. However, the 2D patch attached to a 3D object…

Recent object detectors have achieved impressive accuracy in identifying objects seen during training. However, real-world deployment often introduces novel and unexpected objects, referred to as out-of-distribution (OOD) objects, posing…

Recently, object detection has proven vulnerable to adversarial patch attacks. The attackers holding a specially crafted patch can hide themselves from state-of-the-art detectors, e.g., YOLO, even in the physical world. This attack can…

Object detectors achieve strong performance under nominal imaging conditions but can fail silently when exposed to blur, noise, compression, adverse weather, or resolution changes. In safety-critical settings, it is therefore insufficient…

Nowadays, general object detectors like YOLO and Faster R-CNN as well as their variants are widely exploited in many applications. Many works have revealed that these detectors are extremely vulnerable to adversarial patch attacks. The…

The latest generation of transformer-based vision models has proven to be superior to Convolutional Neural Network (CNN)-based models across several vision tasks, largely attributed to their remarkable prowess in relation modeling.…

As the use of machine learning continues to expand, the importance of ensuring its safety cannot be overstated. A key concern in this regard is the ability to identify whether a given sample is from the training distribution, or is an…

Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against patch attacks. We begin with a set of experiments showing…

Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier. Such approaches have been…

We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of…

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

Large Language Model (LLM)-based agents employ external and internal memory systems to handle complex, goal-oriented tasks, yet this exposes them to severe extraction attacks, and effective defenses remain lacking. In this paper, we propose…

Adversarial patches exemplify the tangible manifestation of the threat posed by adversarial attacks on Machine Learning (ML) models in real-world scenarios. Robustness against these attacks is of the utmost importance when designing…

To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which improves robustness by operations on input data instead of…

Object detection (OD) is critical to real-world vision systems, yet existing backdoor attacks on detection transformers (DETRs) for OD tasks rely on patch-wise triggers optimized at fixed locations with minimal perturbations. Such attacks…

Object detection is a fundamental task in various applications ranging from autonomous driving to intelligent security systems. However, recognition of a person can be hindered when their clothing is decorated with carefully designed…