paper-with-me

Papers

Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach

2024-04-25 · Cristopher McIntyre-Garcia, Adrien Heymans, Beril Borali, Won-Sook Lee, Shiva Nejati

Deep Learning (DL) models excel in computer vision tasks but can be susceptible to adversarial examples. This paper introduces Triple-Metric EvoAttack (TM-EVO), an efficient algorithm for evaluating the robustness of object-detection DL models against adversarial attacks. TM-EVO utilizes a multi-metric fitness function to guide an evolutionary search efficiently in creating effective adversarial test inputs with minimal perturbations. We evaluate TM-EVO on widely-used object-detection DL models, DETR and Faster R-CNN, and open-source datasets, COCO and KITTI. Our findings reveal that TM-EVO outperforms the state-of-the-art EvoAttack baseline, leading to adversarial tests with less noise while maintaining efficiency.

📄 PDF Abstract BibTeX arXiv:2404.17020

Code (1)

cmcin019/tm-evo 공식 구현 pytorch

Tasks

Objectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

Similar Papers 제목 키워드 기반

Attribute-Guided Adversarial Training for Robustness to Natural Perturbations

2020-12-03 · Tejas Gokhale, Rushil Anirudh, Bhavya Kailkhura, Jayaraman J. Thiagarajan 외

While existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real-world settings. In many such cases although test d…

Attribute

DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems

2018-12-27 · Husheng Zhou, Wei Li, Yuankun Zhu, Yuqun Zhang 외

Deep Neural Networks (DNNs) have been widely applied in many autonomous systems such as autonomous driving. Recently, DNN testing has been intensively studied to automatically generate adversarial examples, which inject …

Autonomous DrivingDNN Testing

Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP Inference

2025-11-12 · Chengze Jiang, Minjing Dong, Xinli Shi, Jie Gui arxiv

Vision-language pre-training models (VLPs) demonstrate strong multimodal understanding and zero-shot generalization, yet remain vulnerable to adversarial examples, raising concerns about their reliability. Recent work, T…

Zero-shot GeneralizationAdversarial Robustness

Learning When to Use Adaptive Adversarial Image Perturbations against Autonomous Vehicles

2022-12-28 · Hyung-Jin Yoon, Hamidreza Jafarnejadsani, Petros Voulgaris

The deep neural network (DNN) models for object detection using camera images are widely adopted in autonomous vehicles. However, DNN models are shown to be susceptible to adversarial image perturbations. In the existing…

Autonomous Vehiclesobject-detectionObject DetectionStochastic Optimization

Fast Local Attack: Generating Local Adversarial Examples for Object Detectors

2020-10-27 · Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu 외

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor…

Object