Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning

• URL: http://arxiv.org/abs/2605.05928v1
• Date: Thu, 07 May 2026 09:33:06 GMT
• Title: Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
• Abstract summary: Backdoor attacks pose a serious threat to safety-critical vision systems.<n>Adrial fine-tuning is a common backdoor mitigation approach in classification.<n>We present a detection-aware adversarial fine-tuning framework for mitigating object-detection backdoors.
• Score: 10.393154496941527
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although backdoor mitigation has been studied extensively for image classification, defenses for object detection remain comparatively underdeveloped. Adversarial fine-tuning is a common backdoor mitigation approach in classification, but adapting it to detection is nontrivial as classification-oriented adversarial generation does not match the detection attack space, where attacks may cause object misclassification or disappearance, and standard detection losses can dilute the repair signal across many predictions. We address these challenges through a detection-aware adversarial fine-tuning framework for mitigating object-detection backdoors when the defender has access only to a compromised detector and a small clean dataset, without knowing the attack objective. For adversarial generation that does not require knowledge of the attack objective, we introduce soft-branch minimisation, which uses a soft gate to combine objectives aligned with misclassification and disappearance attacks, together with a detection-aware classification-loss maximisation. For targeted repair, we introduce a dual-objective fine-tuning loss applied to target-matched predictions, concentrating the defensive update on predictions most relevant to the backdoor behaviour. Experiments across CNN- and Transformer-based detectors show that our approach more effectively reduces attack success while preserving true detections, compared with classification-oriented baselines, and maintains competitive clean detection performance.

Related papers

• Fragile Reconstruction: Adversarial Vulnerability of Reconstruction-Based Detectors for Diffusion-Generated Images [32.470971087318695]
  We present a systematic evaluation of the adversarial robustness of three representative detectors across four diverse generative backbone models.<n>We construct adversarial attacks in white-box scenarios, which degrade the performance of all well-trained detectors.<n>We also find that attacks crafted against one detector can be transferred to others, indicating that adversarial attacks on detectors can also be constructed in a black-box setting.
  arXiv  Detail & Related papers  (2026-04-14T14:17:51Z)
• BadDet+: Robust Backdoor Attacks for Object Detection [10.393154496941527]
  We introduce BadDet+, a penalty-based framework that unifies Region Misclassification Attacks (RMA) and Object Disappearance Attacks (ODA)<n>On real-world benchmarks, BadDet+ achieves superior synthetic-to-physical transfer compared to existing RMA and ODA baselines while preserving clean performance.<n>These results highlight significant vulnerabilities in object detection and the necessity for specialized defenses.
  arXiv  Detail & Related papers  (2026-01-28T21:46:33Z)
• AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection [9.539021752700823]
  AnywhereDoor is a multi-target backdoor attack for object detection.<n>It allows adversaries to make objects disappear, fabricate new ones or mislabel them, either across all object classes or specific ones.<n>It improves attack success rates by 26% compared to adaptations of existing methods for such flexible control.
  arXiv  Detail & Related papers  (2025-03-09T09:24:24Z)
• AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection [9.539021752700823]
  AnywhereDoor is a multi-target backdoor attack for object detection.<n>It allows adversaries to make objects disappear, fabricate new ones or mislabel them, either across all object classes or specific ones.<n>It improves attack success rates by 26% compared to adaptations of existing methods for such flexible control.
  arXiv  Detail & Related papers  (2024-11-21T15:50:59Z)
• Spatial-Frequency Discriminability for Revealing Adversarial Perturbations [53.279716307171604]
  Vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. Current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. We propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition.
  arXiv  Detail & Related papers  (2023-05-18T10:18:59Z)
• Object-fabrication Targeted Attack for Object Detection [54.10697546734503]
  adversarial attack for object detection contains targeted attack and untargeted attack. New object-fabrication targeted attack mode can mislead detectors tofabricate extra false objects with specific target labels.
  arXiv  Detail & Related papers  (2022-12-13T08:42:39Z)
• Untargeted Backdoor Attack against Object Detection [69.63097724439886]
  We design a poison-only backdoor attack in an untargeted manner, based on task characteristics. We show that, once the backdoor is embedded into the target model by our attack, it can trick the model to lose detection of any object stamped with our trigger patterns.
  arXiv  Detail & Related papers  (2022-11-02T17:05:45Z)
• Transferable Adversarial Examples for Anchor Free Object Detection [44.7397139463144]
  We present the first adversarial attack on anchor-free object detectors. We leverage high-level semantic information to efficiently generate transferable adversarial examples. Our proposed method achieves state-of-the-art performance and transferability.
  arXiv  Detail & Related papers  (2021-06-03T06:38:15Z)
• Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning [95.60856995067083]
  This work is among the first to perform adversarial defense for ASV without knowing the specific attack algorithms. We propose to perform adversarial defense from two perspectives: 1) adversarial perturbation purification and 2) adversarial perturbation detection. Experimental results show that our detection module effectively shields the ASV by detecting adversarial samples with an accuracy of around 80%.
  arXiv  Detail & Related papers  (2021-06-01T07:10:54Z)
• Detection as Regression: Certified Object Detection by Median Smoothing [50.89591634725045]
  This work is motivated by recent progress on certified classification by randomized smoothing. We obtain the first model-agnostic, training-free, and certified defense for object detection against $ell$-bounded attacks.
  arXiv  Detail & Related papers  (2020-07-07T18:40:19Z)
• Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification [78.51092318750102]
  This work proposes to defend ASV systems against adversarial attacks with a separate detection network. A VGG-like binary classification detector is introduced and demonstrated to be effective on detecting adversarial samples.
  arXiv  Detail & Related papers  (2020-06-11T04:31:56Z)
• A Self-supervised Approach for Adversarial Robustness [105.88250594033053]
  Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems. This paper proposes a self-supervised adversarial training mechanism in the input space. It provides significant robustness against the textbfunseen adversarial attacks.
  arXiv  Detail & Related papers  (2020-06-08T20:42:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.