# From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints

arXiv: https://arxiv.org/abs/2503.04853 · HTML: https://mlsanity.com/paper/2503.04853/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 105 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [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)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [Mitigating Adversarial Effects Through Randomization](https://mlsanity.com/paper/1711.01991/) (2017)
- [Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models](https://mlsanity.com/paper/1805.06605/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality](https://mlsanity.com/paper/1801.02613/) (2018)
- [MagNet: a Two-Pronged Defense against Adversarial Examples](https://mlsanity.com/paper/1705.09064/) (2017)
- [Anti-Backdoor Learning: Training Clean Models on Poisoned Data](https://mlsanity.com/paper/2110.11571/) (2021)
- [Detecting Adversarial Samples from Artifacts](https://mlsanity.com/paper/1703.00410/) (2017)
- [Adversarial Attacks and Defenses in Images, Graphs and Text: A Review](https://mlsanity.com/paper/1909.08072/) (2019)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [A study of the effect of JPG compression on adversarial images](https://mlsanity.com/paper/1608.00853/) (2016)
- [On the (Statistical) Detection of Adversarial Examples](https://mlsanity.com/paper/1702.06280/) (2017)
- [Physical Adversarial Examples for Object Detectors](https://mlsanity.com/paper/1807.07769/) (2018)

## Built on by (most cited first, 1 of 1)

- [Adversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification](https://mlsanity.com/paper/2610.15359/) (2026)

## Abstract (arXiv)

For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all focusing on spatial (or static) imprints within the targeted underlying victim models, we present a fresh temporal paradigm for understanding these attacks. Of paramount discovery is that these imprints are encapsulated within a single loss metric, spanning universally across diverse tasks such as classification and regression, and modalities including image, text, and audio. Recognizing the distinct nature of loss between adversarial and clean examples, we exploit this temporal imprint for AE detection by proposing TRAIT (TRaceable Adversarial temporal trajectory ImprinTs). TRAIT operates under minimal assumptions without prior knowledge of attacks, thereby framing the detection challenge as a one-class classification problem. However, detecting AEs is still challenged by significant overlaps between the constructed synthetic losses of adversarial and clean examples due to the absence of ground truth for incoming inputs. TRAIT addresses this challenge by converting the synthetic loss into a spectrum signature, using the technique of Fast Fourier Transform to highlight the discrepancies, drawing inspiration from the temporal nature of the imprints, analogous to time-series signals. Across 12 AE attacks including SMACK (USENIX Sec'2023), TRAIT demonstrates consistent outstanding performance across comprehensively evaluated modalities, tasks, datasets, and model architectures. In all scenarios, TRAIT achieves an AE detection accuracy exceeding 97%, often around 99%, while maintaining a false rejection rate of 1%. TRAIT remains effective under the formulated strong adaptive attacks.