A Generative Victim Model for Segmentation
We find that the well-trained victim models (VMs), against which the attacks are generated, serve as fundamental prerequisites for adversarial attacks, i.e. a segmentation VM is needed to generate attacks for segmentation. In this context, the victim model is assumed to be robust to achieve effective adversarial perturbation generation. Instead of focusing on improving the robustness of the task-specific victim models, we shift our attention to image generation. From an image generation perspective, we derive a novel VM for segmentation, aiming to generate adversarial perturbations for segmentation tasks without requiring models explicitly designed for image segmentation. Our approach to adversarial attack generation diverges from conventional white-box or black-box attacks, offering a fresh outlook on adversarial attack strategies. Experiments show that our attack method is able to generate effective adversarial attacks with good transferability.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackImage GenerationImage SegmentationmodelSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ConSeg: Contextual Backdoor Attack Against Semantic Segmentation
Despite significant advancements in computer vision, semantic segmentation models may be susceptible to backdoor attacks. These attacks, involving hidden triggers, aim to cause the models to misclassify instances of the …
Semantic SegmentationInfluencer Backdoor Attack on Semantic Segmentation
When a small number of poisoned samples are injected into the training dataset of a deep neural network, the network can be induced to exhibit malicious behavior during inferences, which poses potential threats to real-w…
Backdoor AttackPositionSegmentationSemantic SegmentationEnsemble-based Blackbox Attacks on Dense Prediction
We propose an approach for adversarial attacks on dense prediction models (such as object detectors and segmentation). It is well known that the attacks generated by a single surrogate model do not transfer to arbitrary …
Objectobject-detectionObject DetectionPrediction+1ZeroPur: Succinct Training-Free Adversarial Purification
Adversarial purification is a kind of defense technique that can defend against various unseen adversarial attacks without modifying the victim classifier. Existing methods often depend on external generative models or c…
Adversarial PurificationGAMA: Generative Adversarial Multi-Object Scene Attacks
The majority of methods for crafting adversarial attacks have focused on scenes with a single dominant object (e.g., images from ImageNet). On the other hand, natural scenes include multiple dominant objects that are sem…
Language ModellingObject