mlsanityData to 7 Oct 2026

Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework

arXiv 2109.09829 ↗First posted 20 Sep 2021cs.CR cs.AI cs.ARcited by 17

Not on the map. Why?

Abstract (arXiv)

The security and privacy concerns along with the amount of data that is required to be processed on regular basis has pushed processing to the edge of the computing systems. Deploying advanced Neural Networks (NN), such as deep neural networks (DNNs) and spiking neural networks (SNNs), that offer state-of-the-art results on resource-constrained edge devices is challenging due to the stringent memory and power/energy constraints. Moreover, these systems are required to maintain correct functionality under diverse security and reliability threats. This paper first discusses existing approaches to address energy efficiency, reliability, and security issues at different system layers, i.e., hardware (HW) and software (SW). Afterward, we discuss how to further improve the performance (latency) and the energy efficiency of Edge AI systems through HW/SW-level optimizations, such as pruning, quantization, and approximation. To address reliability threats (like permanent and transient faults), we highlight cost-effective mitigation techniques, like fault-aware training and mapping. Moreover, we briefly discuss effective detection and protection techniques to address security threats (like model and data corruption). Towards the end, we discuss how these techniques can be combined in an integrated cross-layer framework for realizing robust and energy-efficient Edge AI systems.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 59 of its 111 references that are in the map. First posted on arXiv 20 Sep 2021.

Builds on

59 of 111 references.

References · 59

  1. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  4. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  5. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  6. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  7. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  8. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  9. 2017Dynamic Routing Between Capsulescited by 689
  10. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  11. 2017Progressive Neural Architecture Searchcited by 483
  12. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
38 more
  1. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  2. 2015Deep Learning with Limited Numerical Precisioncited by 368
  3. 2016Safety Verification of Deep Neural Networkscited by 262
  4. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 215
  5. 2015Structured Pruning of Deep Convolutional Neural Networkscited by 148
  6. 2016Towards the Science of Security and Privacy in Machine Learningcited by 89
  7. 2017Natural and Effective Obfuscation by Head Inpaintingcited by 60
  8. 2017CryptoDL: Deep Neural Networks over Encrypted Datacited by 56
  9. 2019Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attackscited by 55
  10. 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 40
  11. 2018Chiron: Privacy-preserving Machine Learning as a Servicecited by 38
  12. 2020Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Aheadcited by 34
  13. 2021Q-SpiNN: A Framework for Quantizing Spiking Neural Networkscited by 33
  14. 2020FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networkscited by 32
  15. 2019FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activationcited by 31
  16. 2021SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environmentscited by 29
  17. 2019ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retrainingcited by 28
  18. 2020Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameterscited by 27
  19. 2021CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processorcited by 27
  20. 2018I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Acceleratorscited by 26
  21. 2018Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Acceleratorcited by 25
  22. 2020An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processorcited by 25
  23. 2018QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attackscited by 21
  24. 2020FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networkscited by 21
  25. 2020NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flipscited by 21
  26. 2021SparkXD: A Framework for Resilient and Energy-Efficient Spiking Neural Network Inference using Approximate DRAMcited by 21
  27. 2021DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networkscited by 21
  28. 2021ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memoriescited by 20
  29. 2018ThUnderVolt: Enabling Aggressive Voltage Underscaling and Timing Error Resilience for Energy Efficient Deep Neural Network Acceleratorscited by 17
  30. 2020HarDNN: Feature Map Vulnerability Evaluation in CNNscited by 16
  31. 2020NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networkscited by 16
  32. 2018Toward Scalable Verification for Safety-Critical Deep Networkscited by 12
  33. 2019ROMANet: Fine-Grained Reuse-Driven Off-Chip Memory Access Management and Data Organization for Deep Neural Network Acceleratorscited by 11
  34. 2020DRMap: A Generic DRAM Data Mapping Policy for Energy-Efficient Processing of Convolutional Neural Networkscited by 11
  35. 2021R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensorscited by 9
  36. 2018TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networkscited by 8
  37. 2019CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networkscited by 8
  38. 2018FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learningcited by 7

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 3; 2024: 5; 2025: 2; 2026: 1.

17 papers.

Sort:

By area:

  1. 2022lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agentscited by 18
  2. 2023SwiftTron: An Efficient Hardware Accelerator for Quantized Transformerscited by 17
  3. 2024SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systemscited by 12
  4. 2022fakeWeather: Adversarial Attacks for Deep Neural Networks Emulating Weather Conditions on the Camera Lens of Autonomous Systemscited by 8
  5. 2024Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stackcited by 7
  6. 2022Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systemscited by 6
  7. 2023EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systemscited by 6
  8. 2022Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networkscited by 5
  9. 2022RoHNAS: A Neural Architecture Search Framework with Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networkscited by 4
  10. 2024A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Datacited by 4
  11. 2022tinySNN: Towards Memory- and Energy-Efficient Spiking Neural Networkscited by 3
  12. 2024PENDRAM: Enabling High-Performance and Energy-Efficient Processing of Deep Neural Networks through a Generalized DRAM Data Mapping Policycited by 3
5 more
  1. 2024Enhancing TinyML Security: Study of Adversarial Attack Transferabilitycited by 2
  2. 2025EdgeWisePersona: A Dataset for On-Device User Profiling from Natural Language Interactionscited by 2
  3. 2023RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attackscited by 1
  4. 2025SpikeVox: Towards Energy-Efficient Speech Therapy Framework with Spike-driven Generative Language Modelscited by 0
  5. 2026Scale-Gest: Scalable Model-Space Synthesis and Runtime Selection for On-Device Gesture Detectioncited by 0