# What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction

arXiv: https://arxiv.org/abs/2201.09650 · HTML: https://mlsanity.com/paper/2201.09650/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 84 references that are in the map.
- First posted on arXiv 24 Jan 2022.

## Builds on (most cited first, 30 of 52)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Certified Robustness to Adversarial Examples with Differential Privacy](https://mlsanity.com/paper/1802.03471/) (2018)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models](https://mlsanity.com/paper/1805.06605/) (2018)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Certified Defenses for Data Poisoning Attacks](https://mlsanity.com/paper/1706.03691/) (2017)

## Built on by (most cited first, 11 of 11)

- [Out-of-Distribution Detection with Semantic Mismatch under Masking](https://mlsanity.com/paper/2208.00446/) (2022)
- [Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning](https://mlsanity.com/paper/2209.00005/) (2022)
- [Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors](https://mlsanity.com/paper/2404.12120/) (2024)
- [Non-Cross Diffusion for Semantic Consistency](https://mlsanity.com/paper/2312.00820/) (2023)
- [Universal and Efficient Detection of Adversarial Data through Nonuniform Impact on Network Layers](https://mlsanity.com/paper/2506.20816/) (2025)
- [From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints](https://mlsanity.com/paper/2503.04853/) (2025)
- [EMShepherd: Detecting Adversarial Samples via Side-channel Leakage](https://mlsanity.com/paper/2303.15571/) (2023)
- [Towards Robust Domain Generation Algorithm Classification](https://mlsanity.com/paper/2404.06236/) (2024)
- [T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Driving](https://mlsanity.com/paper/2511.12956/) (2025)
- [Detecting Adversarial Data via Provable Adversarial Noise Amplification](https://mlsanity.com/paper/2605.02109/) (2026)
- [Adversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification](https://mlsanity.com/paper/2610.15359/) (2026)

## Abstract (arXiv)

Adversarial examples (AEs) pose severe threats to the applications of deep neural networks (DNNs) to safety-critical domains, e.g., autonomous driving. While there has been a vast body of AE defense solutions, to the best of our knowledge, they all suffer from some weaknesses, e.g., defending against only a subset of AEs or causing a relatively high accuracy loss for legitimate inputs. Moreover, most existing solutions cannot defend against adaptive attacks, wherein attackers are knowledgeable about the defense mechanisms and craft AEs accordingly. In this paper, we propose a novel AE detection framework based on the very nature of AEs, i.e., their semantic information is inconsistent with the discriminative features extracted by the target DNN model. To be specific, the proposed solution, namely ContraNet, models such contradiction by first taking both the input and the inference result to a generator to obtain a synthetic output and then comparing it against the original input. For legitimate inputs that are correctly inferred, the synthetic output tries to reconstruct the input. On the contrary, for AEs, instead of reconstructing the input, the synthetic output would be created to conform to the wrong label whenever possible. Consequently, by measuring the distance between the input and the synthetic output with metric learning, we can differentiate AEs from legitimate inputs. We perform comprehensive evaluations under various AE attack scenarios, and experimental results show that ContraNet outperforms existing solutions by a large margin, especially under adaptive attacks. Moreover, our analysis shows that successful AEs that can bypass ContraNet tend to have much-weakened adversarial semantics. We have also shown that ContraNet can be easily combined with adversarial training techniques to achieve further improved AE defense capabilities.