# Rethinking Impersonation and Dodging Attacks on Face Recognition Systems

arXiv: https://arxiv.org/abs/2401.08903 · HTML: https://mlsanity.com/paper/2401.08903/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 80 references that are in the map.
- First posted on arXiv 17 Jan 2024.

## Builds on (most cited first, 30 of 62)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models](https://mlsanity.com/paper/2307.14539/) (2023)
- [Enhancing the Transferability of Adversarial Attacks through Variance Tuning](https://mlsanity.com/paper/2103.15571/) (2021)
- [Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples](https://mlsanity.com/paper/2302.04578/) (2023)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [Towards Adversarial Attack on Vision-Language Pre-training Models](https://mlsanity.com/paper/2206.09391/) (2022)
- [Frequency Domain Model Augmentation for Adversarial Attack](https://mlsanity.com/paper/2207.05382/) (2022)
- [Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models](https://mlsanity.com/paper/2307.14061/) (2023)
- [AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning](https://mlsanity.com/paper/2308.07026/) (2023)
- [Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition](https://mlsanity.com/paper/2105.03162/) (2021)
- [LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition](https://mlsanity.com/paper/2101.07922/) (2021)
- [SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing](https://mlsanity.com/paper/1906.07927/) (2019)
- [Improving Adversarial Transferability via Neuron Attribution-Based Attacks](https://mlsanity.com/paper/2204.00008/) (2022)
- [Towards Transferable Adversarial Attack against Deep Face Recognition](https://mlsanity.com/paper/2004.05790/) (2020)
- [Improving Transferability of Adversarial Patches on Face Recognition with Generative Models](https://mlsanity.com/paper/2106.15058/) (2021)
- [Backpropagating Linearly Improves Transferability of Adversarial Examples](https://mlsanity.com/paper/2012.03528/) (2020)
- [Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer](https://mlsanity.com/paper/2203.03121/) (2022)
- [Content-based Unrestricted Adversarial Attack](https://mlsanity.com/paper/2305.10665/) (2023)
- [IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models](https://mlsanity.com/paper/2308.04995/) (2023)
- [Boosting Adversarial Transferability by Block Shuffle and Rotation](https://mlsanity.com/paper/2308.10299/) (2023)

## Built on by (most cited first, 8 of 8)

- [PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation](https://mlsanity.com/paper/2403.09192/) (2024)
- [Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models](https://mlsanity.com/paper/2405.16940/) (2024)
- [DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy](https://mlsanity.com/paper/2501.06533/) (2025)
- [Source-Free Test-Time Adaptation For Online Surface-Defect Detection](https://mlsanity.com/paper/2408.09494/) (2024)
- [Controllable Adversarial Makeup for Privacy via Text-Guided Diffusion](https://mlsanity.com/paper/2503.10549/) (2025)
- [Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation](https://mlsanity.com/paper/2602.23117/) (2026)
- [Signal-based Model Access Risk Analysis for AI System Operations Security](https://mlsanity.com/paper/2607.16414/) (2026)
- [SSM-Attack: Learning Where to Perturb for Black-Box Face Privacy](https://mlsanity.com/paper/2610.17323/) (2026)

## Abstract (arXiv)

Face Recognition (FR) systems can be easily deceived by adversarial examples that manipulate benign face images through imperceptible perturbations. Adversarial attacks on FR encompass two types: impersonation (targeted) attacks and dodging (untargeted) attacks. Previous methods often achieve a successful impersonation attack on FR, however, it does not necessarily guarantee a successful dodging attack on FR in the black-box setting. In this paper, our key insight is that the generation of adversarial examples should perform both impersonation and dodging attacks simultaneously. To this end, we propose a novel attack method termed as Adversarial Pruning (Adv-Pruning), to fine-tune existing adversarial examples to enhance their dodging capabilities while preserving their impersonation capabilities. Adv-Pruning consists of Priming, Pruning, and Restoration stages. Concretely, we propose Adversarial Priority Quantification to measure the region-wise priority of original adversarial perturbations, identifying and releasing those with minimal impact on absolute model output variances. Then, Biased Gradient Adaptation is presented to adapt the adversarial examples to traverse the decision boundaries of both the attacker and victim by adding perturbations favoring dodging attacks on the vacated regions, preserving the prioritized features of the original perturbations while boosting dodging performance. As a result, we can maintain the impersonation capabilities of original adversarial examples while effectively enhancing dodging capabilities. Comprehensive experiments demonstrate the superiority of our method compared with state-of-the-art adversarial attack methods.