# Phantom: A Unified Face-Swap Deepfake Protection Framework with Latent and Spatial Constraints

arXiv: https://arxiv.org/abs/2606.31703 · HTML: https://mlsanity.com/paper/2606.31703/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [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)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [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)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021)
- [FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping](https://mlsanity.com/paper/1912.13457/) (2019)
- [MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices](https://mlsanity.com/paper/1804.07573/) (2018)
- [Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization](https://mlsanity.com/paper/2210.14457/) (2022)
- [Collaborative Diffusion for Multi-Modal Face Generation and Editing](https://mlsanity.com/paper/2304.10530/) (2023)
- [ID-Reveal: Identity-aware DeepFake Video Detection](https://mlsanity.com/paper/2012.02512/) (2020)
- [Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition](https://mlsanity.com/paper/2105.03162/) (2021)
- [Protecting Celebrities from DeepFake with Identity Consistency Transformer](https://mlsanity.com/paper/2203.01318/) (2022)
- [Improving Transferability of Adversarial Patches on Face Recognition with Generative Models](https://mlsanity.com/paper/2106.15058/) (2021)
- [Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer](https://mlsanity.com/paper/2203.03121/) (2022)
- [LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeup](https://mlsanity.com/paper/1904.11272/) (2019)
- [Towards Face Encryption by Generating Adversarial Identity Masks](https://mlsanity.com/paper/2003.06814/) (2020)
- [CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search](https://mlsanity.com/paper/2306.10008/) (2023)
- [DAP: A Dynamic Adversarial Patch for Evading Person Detectors](https://mlsanity.com/paper/2305.11618/) (2023)
- [PAD: Patch-Agnostic Defense against Adversarial Patch Attacks](https://mlsanity.com/paper/2404.16452/) (2024)
- [DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection](https://mlsanity.com/paper/2405.09882/) (2024)
- [Personalized Privacy Protection Mask Against Unauthorized Facial Recognition](https://mlsanity.com/paper/2407.13975/) (2024)

## Abstract (arXiv)

Face-swapping deepfakes pose an escalating threat to personal privacy by enabling unauthorized identity manipulation. While adversarial approaches have demonstrated success against black-box face recognition (FR) models, their applicability to face-swapping scenarios remains underexplored. In particular, reliance on fixed or random targets yields ambiguous latent guidance, and the lack of explicit spatial constraints causes perturbations to spill into identity-irrelevant regions. These issues are further exacerbated by identity-style disentanglement, which suppresses adversarial signals during deepfake generation. In this paper, we present Phantom, a unified face-swap deepfake protection framework that jointly constrains perturbations in latent and spatial domains. Phantom adaptively synthesizes identity-shifted yet attribute-preserving targets to guide identity-aware latent optimization, and applies masked perturbations confined to semantically relevant facial regions. Extensive experiments on state-of-the-art face-swapping deepfakes demonstrate that Phantom improves protection success rates in dodging scenarios by 27.8%, 25.6%, and 16.6% on UniFace, INSwapper, and SimSwap, respectively, while also enhancing visual quality. Furthermore, Phantom generalizes to impersonation scenario, yielding up to 10.2% higher protection while improving perceptual fidelity. These results underscore the effectiveness of jointly leveraging latent and spatial constraints for robust and coherent facial privacy protection.