# FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Features

arXiv: https://arxiv.org/abs/2512.03625 · HTML: https://mlsanity.com/paper/2512.03625/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Visual Adversarial Examples Jailbreak Aligned Large Language Models](https://mlsanity.com/paper/2306.13213/) (2023)
- [Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics](https://mlsanity.com/paper/1612.07767/) (2016)
- [Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them](https://mlsanity.com/paper/2107.11630/) (2021)
- [Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain](https://mlsanity.com/paper/2103.04302/) (2021)
- ["That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks](https://mlsanity.com/paper/2204.04636/) (2022)
- [Detection Defense Against Adversarial Attacks with Saliency Map](https://mlsanity.com/paper/2009.02738/) (2020)
- [Utilizing Network Properties to Detect Erroneous Inputs](https://mlsanity.com/paper/2002.12520/) (2020)
- [Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey](https://mlsanity.com/paper/2404.05219/) (2024)
- [Hamming Similarity and Graph Laplacians for Class Partitioning and Adversarial Image Detection](https://mlsanity.com/paper/2305.01808/) (2023)
- [Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approaches](https://mlsanity.com/paper/2111.12631/) (2021)
- [Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method](https://mlsanity.com/paper/2306.02021/) (2023)
- [Detecting Adversarial Data using Perturbation Forgery](https://mlsanity.com/paper/2405.16226/) (2024)

## Abstract (arXiv)

Although the remarkable performance of deep neural networks (DNNs) in image classification, their vulnerability to adversarial attacks remains a critical challenge. Most existing detection methods rely on complex and poorly interpretable architectures, which compromise interpretability and generalization. To address this, we propose FeatureLens, a lightweight framework that acts as a lens to scrutinize anomalies in image features. Comprising an Image Feature Extractor (IFE) and shallow classifiers (e.g., SVM, MLP, or XGBoost) with model sizes ranging from 1,000 to 30,000 parameters, FeatureLens achieves high detection accuracy ranging from 97.8% to 99.75% in closed-set evaluation and 86.17% to 99.6% in generalization evaluation across FGSM, PGD, CW, and DAmageNet attacks, using only 51 dimensional features. By combining strong detection performance with excellent generalization, interpretability, and computational efficiency, FeatureLens offers a practical pathway toward transparent and effective adversarial defense.