Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift

• URL: http://arxiv.org/abs/2608.19088v1
• Date: Wed, 19 Aug 2026 16:38:39 GMT
• Title: Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift
• Abstract summary: DistScan is a backdoor detection framework based on a simple but previously unexploited observation.<n>It substantially outperforms existing methods, improving average detection accuracy over the best-performing applicable baseline by 27.32 percentage points.
• Score: 35.70747932100589
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object detection models deployed in safety-critical applications remain vulnerable to backdoor attacks that cause targeted misbehaviors when a hidden trigger is present. Existing detection methods either rely on trigger inversion or exploit architecture-specific assumptions, and critically, representative existing methods fail to generalize reliably to scene-level attacks, where a single trigger induces anomalous behavior across all objects in the scene simultaneously. We present DistScan, a backdoor detection framework based on a simple but previously unexploited observation: backdoor injection systematically shifts a model's pre-NMS prediction class distribution away from its training class frequencies, even on clean inputs without any trigger present. DistScan aggregates intermediate class predictions over a clean validation set and flags a model as backdoored if the resulting distribution deviates significantly from the training class frequencies, requiring no model weight access, no trigger knowledge, and no additional training. Extensive experiments on MS-COCO and PASCAL VOC across two architectures and three scene-level attack scenarios demonstrate that DistScan substantially outperforms existing methods, improving average detection accuracy over the best-performing applicable baseline by 27.32 percentage points.

Related papers

• X-WAD: eXplainable Web Anomaly Detection [0.0]
  Modern defenses increasingly model normal behavior, relying on semi-supervised approaches trained on only normal data.<n>This paper investigates the effectiveness of Transformer-based Language Models (TLMs) in the detection of anomalies in HTTP requests.
  arXiv  Detail & Related papers  (2026-08-27T14:23:01Z)
• Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures [19.105669683159302]
  Malicious actors can publish backdoored models that induce specific behaviors in response to predefined triggers.<n>We study the problem of weight-space backdoor detection, where a detector classifier predicts whether a model is malicious using only its weights.<n>We propose Z-PEFT, a lightweight meta-classifier that relies exclusively on layer-wise spectral measures for classification.
  arXiv  Detail & Related papers  (2026-08-03T14:10:54Z)
• Lightweight and Fast Backdoor Model Detection [36.85393813658947]
  DFBScanner is a lightweight static parameter inspection framework for fast backdoor scanning.<n>We show that DFBScanner achieves a 97.17% true-positive rate, 0.95% false-positive rate, and an average detection time of only 1 ms per model.
  arXiv  Detail & Related papers  (2026-05-17T16:02:40Z)
• EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy [66.59724477993339]
  Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to backdoor attacks.<n>We propose EntropyScan, a lightweight and trigger-agnostic method for model-level backdoor detection in LVLMs.<n>Our code will be publicly available soon.
  arXiv  Detail & Related papers  (2026-05-15T08:01:32Z)
• Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning [10.393154496941527]
  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.
  arXiv  Detail & Related papers  (2026-05-07T09:33:06Z)
• Universal Transformation of One-Class Classifiers for Unsupervised Anomaly Detection [51.73001988341294]
  Anomaly detection is typically formulated as a one-class classification problem.<n>We present a dataset folding method that transforms an arbitrary one-class classifier-based anomaly detector into a fully unsupervised method.
  arXiv  Detail & Related papers  (2026-02-13T16:54:12Z)
• Lie Detector: Unified Backdoor Detection via Cross-Examination Framework [68.45399098884364]
  We propose a unified backdoor detection framework in the semi-honest setting.<n>Our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines.<n> Notably, it is the first to effectively detect backdoors in multimodal large language models.
  arXiv  Detail & Related papers  (2025-03-21T06:12:06Z)
• Learning in Multiple Spaces: Few-Shot Network Attack Detection with Metric-Fused Prototypical Networks [47.18575262588692]
  We propose a novel Multi-Space Prototypical Learning framework tailored for few-shot attack detection.<n>By leveraging Polyak-averaged prototype generation, the framework stabilizes the learning process and effectively adapts to rare and zero-day attacks.<n> Experimental results on benchmark datasets demonstrate that MSPL outperforms traditional approaches in detecting low-profile and novel attack types.
  arXiv  Detail & Related papers  (2024-12-28T00:09:46Z)
• Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis [5.8634235309501435]
  We propose a backdoor defense framework tailored to object detection models. By quantifying and analyzing inconsistencies, we develop an algorithm to detect backdoors. Experiments with state-of-the-art two-stage object detectors show our method achieves a 90% improvement in backdoor removal rate.
  arXiv  Detail & Related papers  (2024-09-24T12:58:35Z)
• Model X-ray:Detecting Backdoored Models via Decision Boundary [62.675297418960355]
  Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs) We propose Model X-ray, a novel backdoor detection approach based on the analysis of illustrated two-dimensional (2D) decision boundaries. Our approach includes two strategies focused on the decision areas dominated by clean samples and the concentration of label distribution.
  arXiv  Detail & Related papers  (2024-02-27T12:42:07Z)
• DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows [52.31831255787147]
  We introduce a novel technique, DAAIN, to detect out-of-distribution (OOD) inputs and adversarial attacks (AA) Our approach monitors the inner workings of a neural network and learns a density estimator of the activation distribution. Our model can be trained on a single GPU making it compute efficient and deployable without requiring specialized accelerators.
  arXiv  Detail & Related papers  (2021-05-30T22:07:13Z)
• 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)

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.