mlsanityData to 7 Oct 2026

Downsides of Smartness Across Edge-Cloud Continuum in Modern Industry

arXiv 2603.29289 ↗First posted 31 Mar 2026cs.CR cs.AI cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

The fast pace of modern AI is rapidly transforming traditional industrial systems into vast, intelligent and potentially unmanned autonomous operational environments driven by AI-based solutions. These solutions leverage various forms of machine learning, reinforcement learning, and generative AI. The introduction of such smart capabilities has pushed the envelope in multiple industrial domains, enabling predictive maintenance, optimized performance, and streamlined workflows. These solutions are often deployed across the Industrial Internet of Things (IIoT) and supported by the Edge-Fog-Cloud computing continuum to enable urgent (i.e., real-time or near real-time) decision-making. Despite the current trend of aggressively adopting these smart industrial solutions to increase profit, quality, and efficiency, large-scale integration and deployment also bring serious hazards that if ignored can undermine the benefits of smart industries. These hazards include unforeseen interoperability side-effects and heightened vulnerability to cyber threats, particularly in environments operating with a plethora of heterogeneous IIoT systems. The goal of this study is to shed light on the potential consequences of industrial smartness, with a particular focus on security implications, including vulnerabilities, side effects, and cyber threats. We distinguish software-level downsides stemming from both traditional AI solutions and generative AI from those originating in the infrastructure layer, namely IIoT and the Edge-Cloud continuum. At each level, we investigate potential vulnerabilities, cyber threats, and unintended side effects. As industries continue to become smarter, understanding and addressing these downsides will be crucial to ensure secure and sustainable development of smart industrial systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 54 of its 172 references that are in the map. First posted on arXiv 31 Mar 2026.

Builds on

54 of 172 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  8. 2020Extracting Training Data from Large Language Modelscited by 2,144
  9. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  10. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  11. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  12. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
38 more
  1. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  2. 2016The Mythos of Model Interpretabilitycited by 716
  3. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  4. 2023Prompt Injection attack against LLM-integrated Applicationscited by 568
  5. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 415
  6. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  7. 2024Alignment faking in large language modelscited by 316
  8. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 268
  9. 2018Adversarial Attacks and Defences: A Surveycited by 259
  10. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Surveycited by 215
  11. 2019Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directionscited by 172
  12. 2018Stronger Data Poisoning Attacks Break Data Sanitization Defensescited by 125
  13. 2024PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoningcited by 31
  14. 2024LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systemscited by 20
  15. 2017Software Grand Exposure: SGX Cache Attacks Are Practicalcited by 14
  16. 2016C-FLAT: Control-FLow ATtestation for Embedded Systems Softwarecited by 7
  17. 2025LLM Evaluation Based on Aerospace Manufacturing Expertise: Automated Generation and Multi-Model Question Answeringcited by 7
  18. 2017A Comprehensive Survey on Fog Computing: State-of-the-art and Research Challengescited by 6
  19. 2016Mobile Edge Computing, Fog et al.: A Survey and Analysis of Security Threats and Challengescited by 5
  20. 2025UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learningcited by 5
  21. 2020Analyzing the Performance of Smart Industry 4.0 Applications on Cloud Computing Systemscited by 3
  22. 2021SAED: Edge-Based Intelligence for Privacy-Preserving Enterprise Search on the Cloudcited by 3
  23. 2021Exploring the Impact of Virtualization on the Usability of the Deep Learning Applicationscited by 3
  24. 2024Urgent Edge Computingcited by 3
  25. 2025Navigating the Edge-Cloud Continuum: A State-of-Practice Surveycited by 3
  26. 2019Serverless Edge Computing for Green Oil and Gas Industrycited by 2
  27. 2020Privacy-Preserving Clustering of Unstructured Big Data for Cloud-Based Enterprise Search Solutionscited by 2
  28. 2024Resource Allocation of Industry 4.0 Micro-Service Applications across Serverless Fog Federationcited by 2
  29. 2025Secure Resource Management in Cloud Computing: Challenges, Strategies and Meta-Analysiscited by 2
  30. 2026Decentralized Multi-Agent Swarms for Autonomous Grid Security in Industrial IoT: A Consensus-based Approachcited by 2
  31. 2017Contego: An Adaptive Framework for Integrating Security Tasks in Real-Time Systemscited by 1
  32. 2017A Design-Space Exploration for Allocating Security Tasks in Multicore Real-Time Systemscited by 1
  33. 2018S3BD: Secure Semantic Search over Encrypted Big Data in the Cloudcited by 1
  34. 2019Edge Computing for User-Centric Secure Search on Cloud-Based Encrypted Big Datacited by 1
  35. 2022An Edge-Cloud based Reference Architecture to support cognitive solutions in the Process Industrycited by 1
  36. 2022T4PdM: a Deep Neural Network based on the Transformer Architecture for Fault Diagnosis of Rotating Machinerycited by 1
  37. 2022Edge-MultiAI: Multi-Tenancy of Latency-Sensitive Deep Learning Applications on Edgecited by 1
  38. 2023Federated Fog Computing for Remote Industry 4.0 Applicationscited by 1

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.