mlsanityData to 14 Oct 2026

TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI

arXiv 2602.22238 ↗First posted 24 Feb 2026cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Cloud-edge AI must jointly satisfy model compression and security under tight device budgets. While Tensor-Train Decomposition (TTD) shrinks on-device models, prior selective-encryption studies largely assume dense weights, leaving its practicality under TTD compression unclear. We present TT-SEAL, a selective-encryption framework for TT-decomposed networks. TT-SEAL ranks TT cores with a sensitivity-based importance metric, calibrates a one-time robustness threshold, and uses a value-DP optimizer to encrypt the minimum set of critical cores with AES. Under TTD-aware, transfer-based threat models (and on an FPGA-prototyped edge processor) TT-SEAL matches the robustness of full (black-box) encryption while encrypting as little as 4.89-15.92% of parameters across ResNet-18, MobileNetV2, and VGG-16, and drives the share of AES decryption in end-to-end latency to low single digits (e.g., 58% -> 2.76% on ResNet-18), enabling secure, low-latency edge AI.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 24 Feb 2026.

Builds on

23 of 48 references.

References · 23

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2016Adversarial examples in the physical worldcited by 1,769
  6. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  7. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  8. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  9. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  10. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
  11. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  12. 2019Defending Against Model Stealing Attacks with Adaptive Misinformationcited by 57
11 more
  1. 2022LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinitycited by 39
  2. 2019Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forwardcited by 33
  3. 2023Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesiscited by 18
  4. 2023Tensor Decomposition for Model Reduction in Neural Networks: A Reviewcited by 14
  5. 2023Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learningcited by 11
  6. 2025QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edgecited by 8
  7. 2022Get your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT datacited by 7
  8. 2021Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Servicescited by 5
  9. 2024Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devicescited by 5
  10. 2024TT-SNN: Tensor Train Decomposition for Efficient Spiking Neural Network Trainingcited by 2
  11. 2025ASAP-FE: Energy-Efficient Feature Extraction Enabling Multi-Channel Keyword Spotting on Edge Processorscited by 1

Built on by

Not cited yet.