# Code Division Modulation Layers Against Forgetting and Inference in Continual Gait Identification

arXiv: https://arxiv.org/abs/2607.19122 · HTML: https://mlsanity.com/paper/2607.19122/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning](https://mlsanity.com/paper/1812.00910/) (2018)
- [Continual Representation Learning for Biometric Identification](https://mlsanity.com/paper/2006.04455/) (2020)
- [Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning](https://mlsanity.com/paper/2409.01128/) (2024)
- [Deep Learning-Based Gait Recognition Using Smartphones in the Wild](https://mlsanity.com/paper/1811.00338/) (2018)
- [Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics](https://mlsanity.com/paper/2402.09225/) (2024)
- [Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data](https://mlsanity.com/paper/2304.03980/) (2023)
- [Fingerprint Membership and Identity Inference Against Generative Adversarial Networks](https://mlsanity.com/paper/2406.15253/) (2024)
- [Computationally easy, spectrally good multipliers for congruential pseudorandom number generators](https://mlsanity.com/paper/2001.05304/) (2020)
- [GaitAdapt: Continual Learning for Evolving Gait Recognition](https://mlsanity.com/paper/2508.03375/) (2025)

## Abstract (arXiv)

Continual learning (CL) has been recently employed in biometric identification systems thanks to its ability to integrate new knowledge within a pre-trained model and to the possibility of reducing the computational cost of training. Unfortunately, such approaches pose new challenges both in terms of final accuracy and privacy guarantees since a progressive fine-tuning of the model on small subsets expose them to catastrophic forgetting and successful inference attacks. This paper evaluates the efficiency of code division modulation layers (CDML) on a gait identification system which has been trained following a continual learning policy. The proposed approach preserves accuracy on all the tasks while mitigating membership inference attacks at the same time. Moreover, the impact of retransmission is minimized since replaying data is not necessary.