mlsanityData to 7 Oct 2026

A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

arXiv 2209.07790 ↗First posted 16 Sep 2022cs.CVcited by 55

Not on the map. Why?

Abstract (arXiv)

Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model information. Most existing attack methods aim to minimize the true positive rate, which often shows poor attack performance, as another sub-optimal bounding box may be detected around the attacked bounding box to be the new true positive one. To settle this challenge, we propose to minimize the true positive rate and maximize the false positive rate, which can encourage more false positive objects to block the generation of new true positive bounding boxes. It is modeled as a multi-objective optimization (MOP) problem, of which the generic algorithm can search the Pareto-optimal. However, our task has more than two million decision variables, leading to low searching efficiency. Thus, we extend the standard Genetic Algorithm with Random Subset selection and Divide-and-Conquer, called GARSDC, which significantly improves the efficiency. Moreover, to alleviate the sensitivity to population quality in generic algorithms, we generate a gradient-prior initial population, utilizing the transferability between different detectors with similar backbones. Compared with the state-of-art attack methods, GARSDC decreases by an average 12.0 in the mAP and queries by about 1000 times in extensive experiments. Our codes can be found at https://github.com/LiangSiyuan21/ GARSDC.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). Builds on 31 of its 51 references that are in the map. First posted on arXiv 16 Sep 2022.

Builds on

31 of 51 references.

References · 31

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2017Mask R-CNNcited by 7,259
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  8. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  9. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  10. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  11. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  12. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
19 more
  1. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  2. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  3. 2018Object Detection with Deep Learning: A Reviewcited by 524
  4. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  5. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  6. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  7. 2021Towards Open World Object Detectioncited by 297
  8. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  9. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  10. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  11. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  12. 2018Transferable Adversarial Attacks for Image and Video Object Detectioncited by 109
  13. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
  14. 2020Do Wider Neural Networks Really Help Adversarial Robustness?cited by 79
  15. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  16. 2020DaST: Data-free Substitute Training for Adversarial Attackscited by 60
  17. 2021Boosting Fast Adversarial Training with Learnable Adversarial Initializationcited by 40
  18. 2020Targeted Attack for Deep Hashing based Retrievalcited by 34
  19. 2021QAIR: Practical Query-efficient Black-Box Attacks for Image Retrievalcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 17; 2025: 17; 2026: 12.

55 papers.

Sort:

By area:

  1. 2024Jailbreak Vision Language Models via Bi-Modal Adversarial Promptcited by 103
  2. 2024VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Modelscited by 83
  3. 2023Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimizationcited by 60
  4. 2024Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMscited by 48
  5. 2025Manipulating Multimodal Agents via Cross-Modal Prompt Injectioncited by 42
  6. 2024Visual Adversarial Attack on Vision-Language Models for Autonomous Drivingcited by 35
  7. 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detectioncited by 34
  8. 2024Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearningcited by 31
  9. 2024Effectiveness Assessment of Recent Large Vision-Language Modelscited by 29
  10. 2024Compromising Embodied Agents with Contextual Backdoor Attackscited by 29
  11. 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attackcited by 26
  12. 2024Towards Robust Physical-world Backdoor Attacks on Lane Detectioncited by 25
38 more
  1. 2024Interpreting Object-level Foundation Models via Visual Precision Searchcited by 20
  2. 2022Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentationcited by 19
  3. 2023Does Few-shot Learning Suffer from Backdoor Attacks?cited by 19
  4. 2024LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusionscited by 18
  5. 2023Ensemble-based Blackbox Attacks on Dense Predictioncited by 16
  6. 2025E2AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Modelscited by 12
  7. 2025Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025cited by 11
  8. 2026When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Modelscited by 11
  9. 2023Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attackscited by 10
  10. 2023Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworkscited by 8
  11. 2025Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Drivingcited by 8
  12. 2023Face Encryption via Frequency-Restricted Identity-Agnostic Attackscited by 6
  13. 2024Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threatscited by 6
  14. 20253D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generationcited by 6
  15. 2026CtrlAttack: A Unified Attack on World-Model Control in Diffusion Modelscited by 6
  16. 2026WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agentscited by 6
  17. 2023DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generationcited by 5
  18. 2024TrapFlow: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learningcited by 5
  19. 2024Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysiscited by 4
  20. 2025No Query, No Accesscited by 4
  21. 2025Adversarial Attention Perturbations for Large Object Detection Transformerscited by 4
  22. 2025Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehiclescited by 4
  23. 2025GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbationscited by 3
  24. 2025Physical Adversarial Camouflage through Gradient Calibration and Regularizationcited by 3
  25. 2025MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Drivingcited by 3
  26. 2025Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignmentcited by 3
  27. 2024Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attackscited by 2
  28. 2025Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detectioncited by 2
  29. 2025Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidancecited by 2
  30. 2025Text Adversarial Attacks with Dynamic Outputscited by 2
  31. 2025Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its Derivativescited by 2
  32. 2026Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggerscited by 1
  33. 2026Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspectivecited by 1
  34. 2023Towards Generic and Controllable Attacks Against Object Detectioncited by 0
  35. 2024Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Modelscited by 0
  36. 2025FERD: Fairness-Enhanced Data-Free Robustness Distillationcited by 0
  37. 2026Face anonymization preserving facial expressions and photometric realismcited by 0
  38. 2026R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splattingcited by 0

50 most cited of 55 All 55 (JSON)