# Adversarial Metric Attack and Defense for Person Re-identification

arXiv: https://arxiv.org/abs/1901.10650 · HTML: https://mlsanity.com/paper/1901.10650/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2019.

## Built on by (most cited first, 7 of 7)

- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval](https://mlsanity.com/paper/2103.02927/) (2021)
- [A Person Re-identification Data Augmentation Method with Adversarial Defense Effect](https://mlsanity.com/paper/2101.08783/) (2021)
- [Practical Relative Order Attack in Deep Ranking](https://mlsanity.com/paper/2103.05248/) (2021)
- [On the Robustness of Domain Adaption to Adversarial Attacks](https://mlsanity.com/paper/2108.01807/) (2021)
- [Look Closer to Your Enemy: Learning to Attack via Teacher-Student Mimicking](https://mlsanity.com/paper/2207.13381/) (2022)

## Abstract (arXiv)

Person re-identification (re-ID) has attracted much attention recently due to its great importance in video surveillance. In general, distance metrics used to identify two person images are expected to be robust under various appearance changes. However, our work observes the extreme vulnerability of existing distance metrics to adversarial examples, generated by simply adding human-imperceptible perturbations to person images. Hence, the security danger is dramatically increased when deploying commercial re-ID systems in video surveillance. Although adversarial examples have been extensively applied for classification analysis, it is rarely studied in metric analysis like person re-identification. The most likely reason is the natural gap between the training and testing of re-ID networks, that is, the predictions of a re-ID network cannot be directly used during testing without an effective metric. In this work, we bridge the gap by proposing Adversarial Metric Attack, a parallel methodology to adversarial classification attacks. Comprehensive experiments clearly reveal the adversarial effects in re-ID systems. Meanwhile, we also present an early attempt of training a metric-preserving network, thereby defending the metric against adversarial attacks. At last, by benchmarking various adversarial settings, we expect that our work can facilitate the development of adversarial attack and defense in metric-based applications.