mlsanityData to 7 Oct 2026

Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems

arXiv 2204.09514 ↗First posted 18 Apr 2022cs.AR cs.CR cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

The real-world use cases of Machine Learning (ML) have exploded over the past few years. However, the current computing infrastructure is insufficient to support all real-world applications and scenarios. Apart from high efficiency requirements, modern ML systems are expected to be highly reliable against hardware failures as well as secure against adversarial and IP stealing attacks. Privacy concerns are also becoming a first-order issue. This article summarizes the main challenges in agile development of efficient, reliable and secure ML systems, and then presents an outline of an agile design methodology to generate efficient, reliable and secure ML systems based on user-defined constraints and objectives.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 73 of its 150 references that are in the map. First posted on arXiv 18 Apr 2022.

Builds on

73 of 150 references.

References · 73

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  8. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  9. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  10. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  11. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  12. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
38 more
  1. 2018Scalable Private Learning with PATEcited by 266
  2. 2019MLPerf Inference Benchmarkcited by 195
  3. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  4. 2019Bit-Flip Attack: Crushing Neural Network with Progressive Bit Searchcited by 106
  5. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  6. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 86
  7. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  8. 2018Glow: Graph Lowering Compiler Techniques for Neural Networkscited by 73
  9. 2019Detecting Adversarial Samples Using Influence Functions and Nearest Neighborscited by 72
  10. 2020MLIR: A Compiler Infrastructure for the End of Moore's Lawcited by 64
  11. 2020Towards Flexible Device Participation in Federated Learningcited by 64
  12. 2018TVM: An Automated End-to-End Optimizing Compiler for Deep Learningcited by 62
  13. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 60
  14. 2021Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bitscited by 49
  15. 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 47
  16. 2020The Deep Learning Compiler: A Comprehensive Surveycited by 46
  17. 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 40
  18. 2021AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learningcited by 39
  19. 2018Practical Design Space Explorationcited by 35
  20. 2019A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networkscited by 35
  21. 2020ConfuciuX: Autonomous Hardware Resource Assignment for DNN Accelerators using Reinforcement Learningcited by 35
  22. 2020Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Aheadcited by 34
  23. 2019FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activationcited by 31
  24. 2020Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradientcited by 31
  25. 2020Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insightscited by 27
  26. 2020Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameterscited by 27
  27. 2021CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processorcited by 27
  28. 2018I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Acceleratorscited by 26
  29. 2020AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICscited by 26
  30. 2018Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Acceleratorcited by 25
  31. 2020An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processorcited by 25
  32. 2021NAAS: Neural Accelerator Architecture Searchcited by 24
  33. 2017Biologically inspired protection of deep networks from adversarial attackscited by 23
  34. 2021Comparing Representations in Tracking for Event Camera-based SLAMcited by 23
  35. 2020Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Startcited by 22
  36. 2021Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottleneckscited by 22
  37. 2018QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attackscited by 21
  38. 2020FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networkscited by 21

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 1.

6 papers.

  1. 2023SwiftTron: An Efficient Hardware Accelerator for Quantized Transformerscited by 17
  2. 2022fakeWeather: Adversarial Attacks for Deep Neural Networks Emulating Weather Conditions on the Camera Lens of Autonomous Systemscited by 8
  3. 2024Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stackcited by 7
  4. 2022RoHNAS: A Neural Architecture Search Framework with Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networkscited by 4
  5. 2023RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attackscited by 1
  6. 2023Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerancecited by 1