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

arXiv: https://arxiv.org/abs/2602.22238 · HTML: https://mlsanity.com/paper/2602.22238/

## 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 (most cited first, 23 of 23)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks](https://mlsanity.com/paper/1908.06281/) (2019)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Enhancing the Transferability of Adversarial Attacks through Variance Tuning](https://mlsanity.com/paper/2103.15571/) (2021)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [Defending Against Model Stealing Attacks with Adaptive Misinformation](https://mlsanity.com/paper/1911.07100/) (2019)
- [LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity](https://mlsanity.com/paper/2207.13129/) (2022)
- [Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forward](https://mlsanity.com/paper/1905.12762/) (2019)
- [Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis](https://mlsanity.com/paper/2303.03808/) (2023)
- [Tensor Decomposition for Model Reduction in Neural Networks: A Review](https://mlsanity.com/paper/2304.13539/) (2023)
- [Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning](https://mlsanity.com/paper/2306.15333/) (2023)
- [QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge](https://mlsanity.com/paper/2503.16709/) (2025)
- [Get your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT data](https://mlsanity.com/paper/2201.04569/) (2022)
- [Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services](https://mlsanity.com/paper/2105.12344/) (2021)
- [Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices](https://mlsanity.com/paper/2412.09289/) (2024)
- [TT-SNN: Tensor Train Decomposition for Efficient Spiking Neural Network Training](https://mlsanity.com/paper/2401.08001/) (2024)
- [ASAP-FE: Energy-Efficient Feature Extraction Enabling Multi-Channel Keyword Spotting on Edge Processors](https://mlsanity.com/paper/2506.14657/) (2025)

## 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.