# Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency

arXiv: https://arxiv.org/abs/2007.09763 · HTML: https://mlsanity.com/paper/2007.09763/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2020.

## Built on by (most cited first, 16 of 16)

- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations](https://mlsanity.com/paper/2110.01823/) (2021)
- [SoK: On the Semantic AI Security in Autonomous Driving](https://mlsanity.com/paper/2203.05314/) (2022)
- [Context-Aware Transfer Attacks for Object Detection](https://mlsanity.com/paper/2112.03223/) (2021)
- [Zero-Query Transfer Attacks on Context-Aware Object Detectors](https://mlsanity.com/paper/2203.15230/) (2022)
- [GAMA: Generative Adversarial Multi-Object Scene Attacks](https://mlsanity.com/paper/2209.09502/) (2022)
- [Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes](https://mlsanity.com/paper/2108.08421/) (2021)
- [Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency](https://mlsanity.com/paper/2108.09891/) (2021)
- [ADC: Adversarial attacks against object Detection that evade Context consistency checks](https://mlsanity.com/paper/2110.12321/) (2021)
- [FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers](https://mlsanity.com/paper/2401.01752/) (2024)
- [TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification](https://mlsanity.com/paper/2302.02023/) (2023)
- [Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks](https://mlsanity.com/paper/2404.15881/) (2024)
- [PRAT: PRofiling Adversarial aTtacks](https://mlsanity.com/paper/2309.11111/) (2023)
- [Releasing Inequality Phenomenon in ℓ∞-norm Adversarial Training via Input Gradient Distillation](https://mlsanity.com/paper/2305.09305/) (2023)
- [On Feasibility of Intent Obfuscating Attacks](https://mlsanity.com/paper/2408.02674/) (2024)
- [Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation](https://mlsanity.com/paper/2606.09536/) (2026)

## Abstract (arXiv)

There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs) in machine vision; most of these perturbation-based attacks target object classifiers. Inspired by the observation that humans are able to recognize objects that appear out of place in a scene or along with other unlikely objects, we augment the DNN with a system that learns context consistency rules during training and checks for the violations of the same during testing. Our approach builds a set of auto-encoders, one for each object class, appropriately trained so as to output a discrepancy between the input and output if an added adversarial perturbation violates context consistency rules. Experiments on PASCAL VOC and MS COCO show that our method effectively detects various adversarial attacks and achieves high ROC-AUC (over 0.95 in most cases); this corresponds to over 20% improvement over a state-of-the-art context-agnostic method.