# On the Reconstruction of Face Images from Deep Face Templates

arXiv: https://arxiv.org/abs/1703.00832 · HTML: https://mlsanity.com/paper/1703.00832/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2017.

## Built on by (most cited first, 30 of 67)

- [Heterogeneous Federated Learning: State-of-the-art and Research Challenges](https://mlsanity.com/paper/2307.10616/) (2023)
- [Arc2Face: A Foundation Model for ID-Consistent Human Faces](https://mlsanity.com/paper/2403.11641/) (2024)
- [A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges](https://mlsanity.com/paper/2206.13732/) (2022)
- [Biometrics: Trust, but Verify](https://mlsanity.com/paper/2105.06625/) (2021)
- [FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude](https://mlsanity.com/paper/2306.17206/) (2023)
- [Privacy-preserving Adversarial Facial Features](https://mlsanity.com/paper/2305.05391/) (2023)
- [Privacy-Preserving Face Recognition Using Trainable Feature Subtraction](https://mlsanity.com/paper/2403.12457/) (2024)
- [An Overview of Privacy-enhancing Technologies in Biometric Recognition](https://mlsanity.com/paper/2206.10465/) (2022)
- [An Equivalence Between Data Poisoning and Byzantine Gradient Attacks](https://mlsanity.com/paper/2202.08578/) (2022)
- [Towards Protecting Face Embeddings in Mobile Face Verification Scenarios](https://mlsanity.com/paper/2110.00434/) (2021)
- [Deep Face Fuzzy Vault: Implementation and Performance](https://mlsanity.com/paper/2102.02458/) (2021)
- [HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption](https://mlsanity.com/paper/2403.14111/) (2024)
- [Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques](https://mlsanity.com/paper/2110.05044/) (2021)
- [IronMask: Modular Architecture for Protecting Deep Face Template](https://mlsanity.com/paper/2104.02239/) (2021)
- [Face Reconstruction from Face Embeddings using Adapter to a Face Foundation Model](https://mlsanity.com/paper/2411.03960/) (2024)
- [SlerpFace: Face Template Protection via Spherical Linear Interpolation](https://mlsanity.com/paper/2407.03043/) (2024)
- [Darker than Black-Box: Face Reconstruction from Similarity Queries](https://mlsanity.com/paper/2106.14290/) (2021)
- [Deep Learning Approaches for Seizure Video Analysis: A Review](https://mlsanity.com/paper/2312.10930/) (2023)
- [An Attack on Facial Soft-biometric Privacy Enhancement](https://mlsanity.com/paper/2111.12405/) (2021)
- [MLP-Hash: Protecting Face Templates via Hashing of Randomized Multi-Layer Perceptron](https://mlsanity.com/paper/2204.11054/) (2022)
- [Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction](https://mlsanity.com/paper/2412.10448/) (2024)
- [HEFT: Homomorphically Encrypted Fusion of Biometric Templates](https://mlsanity.com/paper/2208.07241/) (2022)
- [Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition](https://mlsanity.com/paper/2209.04920/) (2022)
- [Differentially Private Gradient Flow based on the Sliced Wasserstein Distance](https://mlsanity.com/paper/2312.08227/) (2023)
- [Reversing the Irreversible: A Survey on Inverse Biometrics](https://mlsanity.com/paper/2401.02861/) (2024)
- [CLIP-FTI: Fine-Grained Face Template Inversion via CLIP-Driven Attribute Conditioning](https://mlsanity.com/paper/2512.15433/) (2025)
- [Canonical Face Embeddings](https://mlsanity.com/paper/2106.07822/) (2021)
- [Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2210.11237/) (2022)
- [Face Reconstruction Transfer Attack as Out-of-Distribution Generalization](https://mlsanity.com/paper/2407.02403/) (2024)
- [CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning](https://mlsanity.com/paper/2503.00062/) (2025)

## Abstract (arXiv)

State-of-the-art face recognition systems are based on deep (convolutional) neural networks. Therefore, it is imperative to determine to what extent face templates derived from deep networks can be inverted to obtain the original face image. In this paper, we study the vulnerabilities of a state-of-the-art face recognition system based on template reconstruction attack. We propose a neighborly de-convolutional neural network (textitNbNet) to reconstruct face images from their deep templates. In our experiments, we assumed that no knowledge about the target subject and the deep network are available. To train the textitNbNet reconstruction models, we augmented two benchmark face datasets (VGG-Face and Multi-PIE) with a large collection of images synthesized using a face generator. The proposed reconstruction was evaluated using type-I (comparing the reconstructed images against the original face images used to generate the deep template) and type-II (comparing the reconstructed images against a different face image of the same subject) attacks. Given the images reconstructed from textitNbNets, we show that for verification, we achieve TAR of 95.20% (58.05%) on LFW under type-I (type-II) attacks @ FAR of 0.1%. Besides, 96.58% (92.84%) of the images reconstruction from templates of partition textitfa (textitfb) can be identified from partition textitfa in color FERET. Our study demonstrates the need to secure deep templates in face recognition systems.