Adversarial Attacks on Object Detectors

Latest papers

20 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Can Attack Difficulty Be Characterized Before Optimization? A Study of Pre-optimization Difficulty in Person-Vanishing Attacks
Sep 28, 2026Jingyao Xu, Dongdong Wang, Siyang LuAdversarial Attacks Object Detection
School of Computer Science and Technology, Beijing Jiaotong University · College of Design, Construction, and Planning, University of Florida
ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity
Aug 30, 2026Haoran Wang, Matthew Lau, Alec Helbling +7Adversarial Robustness Adversarial Training
Georgia Institute of Technology, Atlanta, GA, USA · Khalifa University, Abu Dhabi, UAE · Technology Innovation Institute, Abu Dhabi, UAE
AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Driving
Aug 17, 2026Yuting Wu, Dongfang Guo, Xiangzhong Luo +2Adversarial Robustness Object Detection
Nanyang Technological University, Singapore · City University of Hong Kong, Hong Kong SAR, China
AdvTiles: Physical Adversarial Camouflage Clothing against Person Detectors via Learnable Tiles
Aug 7, 2026Jinlei Wang, Jiahuan Long, Mingkai Sun +9Adversarial Attacks Adversarial Attacks on Object Detectors
Sun Yat-sen University · 2Chinese Academy of Military Science · 3Shenzhen University +2
Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers
Aug 7, 2026Ridma Jayasundara, Shaheer Mohamed, Tharindu Fernando +6Adversarial Attacks Adversarial Robustness
Signal Processing, Artificial Intelligence and Vision Technologies Group (SAIVT), Queensland University of Technology · Institute of High-Performance Computing, Agency for Science, Technology and Research, Singapore · School of Computing, National University of Singapore +1
ColorFD: A Finite-Difference Guided Black-Box Physical Adversarial Attack for Remote Sensing Object Detection
Aug 5, 2026Tiannuo Guo, Guhang Qiu, Yuzhen Xie +3Remote Sensing Image Understanding Adversarial Patch Attacks
College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
Fast Object Removal Attacks on Safety-Critical Video-based Perception Systems
Aug 3, 2026Mohammad Imtiaz Hasan, M Sabbir Salek, Nathan Jones +2Adversarial Attacks Adversarial Attacks on Object Detectors
Glenn Department of Civil Engineering, Clemson University, Clemson, SC 29634 · National Center for Transportation Cybersecurity and Resiliency, Greenville, SC 29607 · School of Computing, Clemson University, Clemson, SC 29634 +1
Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks
Jul 23, 2026Yuanhao Huang, Yilong Ren, Jinlei Wang +3Adversarial Training Adversarial Robustness
School of Transportation Science and Engineering, Beihang University, 100191, Beijing, P.R China · Zhongguancun Laboratory, 100191, Beijing, P.R China · School of Systems Science and Engineering, Sun Yat-Sen University, 510006, Guangzhou, P.R China +2
ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments
Jul 19, 2026Mansi Phute, Alexander Greenhalgh, Matthew Hull +8Object Detection Physical Adversarial Attacks
Georgia Institute of Technology, USA · Technological Innovation Institute, UAE
AdvSerial: Physical Adversarial Attacks on Infrastructure-mounted Pedestrian Detectors via Semantic Feature Suppression
Jul 19, 2026Yuanhao Huang, Yilong Ren, Jinlei Wang +3Adversarial Patch Attacks Adversarial Attacks
School of Transportation Science and Engineering, Beihang University, 100191, Beijing, P.R China · Zhongguancun Laboratory, 100191, Beijing, P.R China · School of Systems Science and Engineering, Sun Yat-Sen University, 510006, Guangzhou, P.R China +1
LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detection
Jul 6, 2026Vincent Lébé, Yannick Prudent, Corentin Friedrich +3Adversarial Robustness Object Detection
IRIT, DTIPG - SNCF, UT3 · IRT Saint-Exup´ery · Alstom +2
Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors
Jun 29, 2026Chengzeng You, Binbin Xu, Soteris DemetriouFeature Attribution Lidar-Based 3D Object Detection
Imperial College London, UK · Now at Google.
VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasion
Jun 18, 2026Shihui Yan, Hu Liu, Junyu Shi +6Adversarial Attacks Adversarial Attacks on Object Detectors
State Key Laboratory of Intelligent Vehicle Safety Technology · School of Cyber Science and Engineering, Huazhong University of Science and Technology · School of Computer Science and Technology, Huazhong University of Science and Technology +2
Budget-Aware Adaptive Adversarial Patches for Black-Box Object Detection
Jun 16, 2026Pedram MohajerAnsari, Amir Salarpour, David Fernandez +1Adversarial Patch Attacks Object Detection
School of Computing, Clemson University, USA
Structured Adversarial Camouflage via Voronoi Diagrams
Jun 16, 2026Jens Bayer, Stefan Becker, David Münch +2Adversarial Patch Attacks Object Detection
Fraunhofer IOSB and Fraunhofer Center for Machine Learning · Karlsruhe Institute of Technology
Adversarial Robustness Analysis of Cloud-Assisted Autonomous Driving Systems
Apr 6, 2026Maher Al Islam, Amr S. El-WakeelAdversarial Attacks on Object Detectors Adversarial Robustness
Lane Department of Computer Science and Electrical Engineering, West Virginia University, WV, USA
Fluently Lying: Adversarial Robustness Can Be Substrate-Dependent
Apr 1, 2026Daye Kang, Hyeongboo BaekAdversarial Attacks on Object Detectors Adversarial Robustness
University of Seoul, Seoul, South Korea
A Unified Spatial Alignment Framework for Highly Transferable Transformation-Based Attacks on Spatially Structured Tasks
Mar 26, 2026Jiaming Liang, Chi-Man PunAdversarial Attacks on Object Detectors Adversarial Attacks
University of Macau
In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing
Mar 19, 2026Xiao Fang, Yiming Gong, Stanislav Panev +4Adversarial Attacks on Object Detectors Object Detection
Carnegie Mellon University · DEVCOM Army Research Laboratory · Florida State University
Benchmarking Adversarial Robustness and Adversarial Training Strategies for Object Detection
Feb 18, 2026Alexis Winter, Jean-Vincent Martini, Romaric Audigier +2Adversarial Attacks on Object Detectors Adversarial Robustness
Universit´e Paris-Saclay, CEA, List, F-91191, Palaiseau, France.

Sep 28, 2026J/K move · Enter open · S save

Can Attack Difficulty Be Characterized Before Optimization? A Study of Pre-optimization Difficulty in Person-Vanishing Attacks

Jingyao Xu, Dongdong Wang, Siyang Lu

School of Computer Science and Technology, Beijing Jiaotong University · College of Design, Construction, and Planning, University of Florida

Adversarial Attacks Object Detection Adversarial Attacks on Object Detectors

Open paper AskPDF arXiv

Adversarial attacks against object detectors are traditionally studied from an optimization perspective, where attack difficulty is regarded as an outcome observed only after adversarial optimization. This raises a fundamental question: can the relative attack difficulty of different inputs be characterized before optimization begins? In this paper, we investigate this question for person-vanishing attacks by introducing the concept of pre-optimization attack difficulty, which captures intrinsic differences in optimization effort across input images. To estimate this latent difficulty before optimization, we propose Quad-CLEVER, an efficient geometry-based estimator derived from a quadratic approximation of the local person-vanishing margin along the most attack-relevant direction. Extensive experiments across multiple attack algorithms demonstrate that Quad-CLEVER consistently correlates with the observed optimization cost, providing empirical evidence that attack difficulty exhibits a predictable pre-optimization structure. Building upon this finding, we further propose a difficulty-aware attack framework that leverages the estimated difficulty to adaptively allocate optimization budgets for a base attack under a fixed computational budget. On BDD100K, the proposed framework improves the image-level attack success rate by up to 5.78

\%

while reducing the average optimization cost by up to 11.42 iterations. On the more challenging EventPed dataset, it saves 2.25 optimization iterations while maintaining comparable attack performance. These results demonstrate that attack difficulty can be meaningfully estimated before optimization and that exploiting such estimates enables more computationally efficient adversarial attacks.