mlsanityData to 14 Oct 2026

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

arXiv 2607.19122 ↗First posted 21 Jul 2026cs.MM cs.AI cs.CRcited by 0

Not on the map. Why?

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.

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

11 of 25 references.

References · 11

  1. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  2. 2021Membership Inference Attacks From First Principlescited by 878
  3. 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 77
  4. 2020Continual Representation Learning for Biometric Identificationcited by 25
  5. 2024Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learningcited by 23
  6. 2018Deep Learning-Based Gait Recognition Using Smartphones in the Wildcited by 19
  7. 2024Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometricscited by 13
  8. 2023Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Datacited by 9
  9. 2024Fingerprint Membership and Identity Inference Against Generative Adversarial Networkscited by 2
  10. 2020Computationally easy, spectrally good multipliers for congruential pseudorandom number generatorscited by 1
  11. 2025GaitAdapt: Continual Learning for Evolving Gait Recognitioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Binarized Neural Networks for Resource-Constrained On-Device Gait Identification
  2. 2025GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesis
  3. 2025Gait Recognition via Collaborating Discriminative and Generative Diffusion Models
  4. 2026GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition
  5. 2026GaitProtector: Impersonation-Driven Gait De-Identification via Training-Free Diffusion Latent Optimization
  6. 2025CLAD-Net: Continual Activity Recognition in Multi-Sensor Wearable Systems
  7. 2025Unsupervised Domain Adaptation with Dynamic Clustering and Contrastive Refinement for Gait Recognition
  8. 2023Kaizen: Practical Self-supervised Continual Learning with Continual Fine-tuning