# Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspection

arXiv: https://arxiv.org/abs/1905.09186 · HTML: https://mlsanity.com/paper/1905.09186/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2019.

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

- [Adversarial Example Detection for DNN Models: A Review and Experimental Comparison](https://mlsanity.com/paper/2105.00203/) (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)
- [Revisiting Model's Uncertainty and Confidences for Adversarial Example Detection](https://mlsanity.com/paper/2103.05354/) (2021)
- [Threat Assessment in Machine Learning based Systems](https://mlsanity.com/paper/2207.00091/) (2022)
- [PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis](https://mlsanity.com/paper/2404.10789/) (2024)
- [ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack](https://mlsanity.com/paper/2408.05479/) (2024)
- [MetaSel: A Test Selection Approach for Fine-tuned DNN Models](https://mlsanity.com/paper/2503.17534/) (2025)
- [Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems](https://mlsanity.com/paper/2512.23132/) (2025)
- [MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis](https://mlsanity.com/paper/2104.10076/) (2021)
- [Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples](https://mlsanity.com/paper/2107.00561/) (2021)
- [DAD: Data-free Adversarial Defense at Test Time](https://mlsanity.com/paper/2204.01568/) (2022)
- [Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations](https://mlsanity.com/paper/2206.15128/) (2022)
- [DAD++: Improved Data-free Test Time Adversarial Defense](https://mlsanity.com/paper/2309.05132/) (2023)
- [AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation](https://mlsanity.com/paper/2404.12635/) (2024)
- [LogitDynamics: Reliable ViT Error Detection from Layerwise Logit Trajectories](https://mlsanity.com/paper/2604.10643/) (2026)

## Abstract (arXiv)

Despite having excellent performances for a wide variety of tasks, modern neural networks are unable to provide a reliable confidence value allowing to detect misclassifications. This limitation is at the heart of what is known as an adversarial example, where the network provides a wrong prediction associated with a strong confidence to a slightly modified image. Moreover, this overconfidence issue has also been observed for regular errors and out-of-distribution data. We tackle this problem by what we call introspection, i.e. using the information provided by the logits of an already pretrained neural network. We show that by training a simple 3-layers neural network on top of the logit activations, we are able to detect misclassifications at a competitive level.