pith. sign in

arxiv: 1907.02506 · v1 · pith:CGUMNRKPnew · submitted 2019-07-04 · 💻 cs.DC · cs.CR· cs.NI

Security modeling and efficient computation offloading for service workflow in mobile edge computing

Binbin Huang , Zhongjin Lia , Peng Tang , Shangguang Wang , Jun Zhao , Haiyang Hua , Wanqing Lia , Victor Chang This is my paper

Pith reviewed 2026-05-25 08:45 UTC · model grok-4.3

classification 💻 cs.DC cs.CRcs.NI
keywords computation offloadingmobile edge computingsecurity modelingenergy efficiencyservice workflowgenetic algorithmrisk probabilitydeadline constraint
0
0 comments X

The pith

SEECO uses a genetic algorithm to minimize energy for workflow tasks offloaded to MEC servers while respecting risk probability and deadline constraints.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes a security and energy efficient computation offloading strategy called SEECO for service workflows running on resource-limited mobile devices in a mobile edge computing environment. It first constructs a model that estimates the extra time required by security services at chosen risk levels. The offloading decision then selects for each task both its execution location and its security services so that total energy on the mobile device stays low while the overall risk stays below a threshold and the workflow finishes by its deadline. A genetic algorithm encodes the ordering of tasks, their locations, and security choices to search for good solutions. Experiments across different workflow sizes and structures show the resulting schedules use less energy than alternatives while satisfying the security and timing rules.

Core claim

By building an explicit security overhead model and encoding task location, execution order, and security service selection inside a genetic algorithm, the SEECO strategy produces offloading plans that keep workflow risk probability and completion time inside given bounds while reducing the energy drawn from the mobile device.

What carries the argument

SEECO formulation that adds a security overhead model to the classic energy-plus-time offloading objective and solves it with a genetic algorithm whose chromosomes represent task ordering, placement, and security level choices.

If this is right

  • Mobile devices can run complex workflows with lower battery drain while keeping external attack risk below a chosen threshold.
  • Workflow deadlines remain met even after security services are inserted at selected risk levels.
  • The same encoding and search method applies when the number of tasks or the number of available edge servers changes.
  • Energy savings appear consistently across different workflow shapes and parameter settings in simulation.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the overhead model is portable to other threat models, the same optimization loop could handle additional constraints such as data locality or monetary cost.
  • Real-device deployment would need to re-calibrate the model because simulation may omit radio and OS scheduling effects.
  • The approach implies that security need not be treated as an afterthought; it can be folded into the placement decision without destroying feasibility.

Load-bearing premise

The security overhead model built in the paper accurately measures the execution time of security services for the chosen risk levels.

What would settle it

Measure the actual wall-clock time required to run each security service at each risk level on representative edge hardware and compare those times against the model's predictions; large discrepancies would invalidate the optimized schedules.

Figures

Figures reproduced from arXiv: 1907.02506 by Binbin Huang, Haiyang Hua, Jun Zhao, Peng Tang, Shangguang Wang, Victor Chang, Wanqing Lia, Zhongjin Lia.

Figure 1
Figure 1. Figure 1: Fig.1. The architectur [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 5
Figure 5. Figure 5: illustrate the security-aware task execution process. Task 𝑖𝑖 and task 𝑖𝑖+1 are the immediate successors of task 𝑖𝑖−1. We assume task 𝑖𝑖 and task 𝑖𝑖−1 are executed on VM 𝑣𝑣𝑣𝑣𝑛𝑛 𝑞𝑞 and 𝑣𝑣𝑣𝑣 , respectively. When task 𝑖𝑖−1 is finished, the output data 𝛽𝛽𝑖𝑖−1 of task 𝑖𝑖−1 is transferred to its successor task 𝑖𝑖, and the corresponding transfer time 𝑇𝑇𝑇𝑇𝑇𝑇( 𝑖𝑖−1) can be computed by Eq. (9). 𝑇𝑇𝑇𝑇𝑇𝑇( 𝑖𝑖−1) = ⎩ ⎪ ⎨… view at source ↗
Figure 6
Figure 6. Figure 6: An example of a workflow [PITH_FULL_IMAGE:figures/full_fig_p015_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Encoding scheme of a valid schedule for the [PITH_FULL_IMAGE:figures/full_fig_p015_7.png] view at source ↗
read the original abstract

It is a big challenge for resource-limited mobile devices (MDs) to execute various complex and energy-consumed mobile applications. Fortunately, as a novel computing paradigm, edge computing (MEC) can provide abundant computing resources to execute all or parts of the tasks of MDs and thereby can greatly reduce the energy of MD and improve the QoS of applications. However, offloading workflow tasks to the MEC servers are liable to external security threats (e.g., snooping, alteration). In this paper, we propose a security and energy efficient computation offloading (SEECO) strategy for service workflows in MEC environment, the goal of which is to optimize the energy consumption under the risk probability and deadline constraints. First, we build a security overhead model to measure the execution time of security services. Then, we formulate the computation offloading problem by incorporating the security, energy consumption and execution time of workflow application. Finally, based on the genetic algorithm (GA), the corresponding coding strategies of SEECO are devised by considering tasks execution order and location and security services selection. Extensive experiments with the variety of workflow parameters demonstrate that SEECO strategy can achieve the security and energy efficiency for the mobile applications.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper proposes SEECO, a security and energy efficient computation offloading strategy for service workflows in MEC. It first constructs a security overhead model to quantify execution time of security services at chosen risk levels, then formulates an optimization problem that jointly accounts for security risk probability, energy consumption, and deadline constraints on workflow tasks. Finally, it applies a genetic algorithm whose chromosome encodes task execution order, offloading location (local vs. MEC), and security service selection; experiments varying workflow parameters are reported to show that SEECO meets the constraints while reducing energy relative to baselines.

Significance. If the security overhead model proves accurate and the GA solutions are shown to be near-optimal, the work would supply a concrete, implementable method for balancing security, energy, and latency in MEC offloading—an area of practical importance for resource-constrained mobile devices. The explicit incorporation of risk-level-dependent security overhead into the objective and the GA coding scheme constitute reusable technical contributions.

major comments (2)
  1. [§3] §3 (Security Overhead Model): the model that maps risk level to execution time of each security service is load-bearing for both the subsequent formulation and all experimental claims, yet the manuscript supplies neither empirical measurements of real primitives (e.g., AES encryption latency at varying key lengths or risk parameters) nor any cross-validation against hardware traces. Without this grounding, the reported energy savings cannot be distinguished from artifacts of the unverified timing functions.
  2. [§5] §5 (Experiments): the claim that “extensive experiments with the variety of workflow parameters demonstrate that SEECO strategy can achieve the security and energy efficiency” is unsupported by any reported baseline algorithms, statistical significance tests, or sensitivity analysis on the security-model parameters; the single set of curves therefore does not establish robustness of the central efficiency claim.
minor comments (2)
  1. [Abstract / §4] The abstract and §4 refer to “risk probability” without defining how the probability is computed from the chosen risk level; a short clarifying paragraph or equation would remove ambiguity.
  2. [Figures in §5] Table captions and axis labels in the experimental figures should explicitly state the units of energy (Joules) and the precise definition of the risk metric.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major point below, indicating where revisions will be made to strengthen the manuscript.

read point-by-point responses

  1. Referee: [§3] §3 (Security Overhead Model): the model that maps risk level to execution time of each security service is load-bearing for both the subsequent formulation and all experimental claims, yet the manuscript supplies neither empirical measurements of real primitives (e.g., AES encryption latency at varying key lengths or risk parameters) nor any cross-validation against hardware traces. Without this grounding, the reported energy savings cannot be distinguished from artifacts of the unverified timing functions.

    Authors: We agree that the security overhead model would be strengthened by empirical grounding. The model uses analytical expressions parameterized by standard values drawn from security literature rather than new hardware traces. In revision we will expand §3 with additional citations to measured overhead studies for comparable primitives, add an explicit discussion of model assumptions and limitations, and include sensitivity analysis on the timing parameters within the experimental section. New hardware measurements are outside the scope of the current work. revision: partial

  2. Referee: [§5] §5 (Experiments): the claim that “extensive experiments with the variety of workflow parameters demonstrate that SEECO strategy can achieve the security and energy efficiency” is unsupported by any reported baseline algorithms, statistical significance tests, or sensitivity analysis on the security-model parameters; the single set of curves therefore does not establish robustness of the central efficiency claim.

    Authors: We accept that the experimental section requires clearer baselines and additional statistical support. The current results vary workflow parameters but do not explicitly label or compare against named baselines. In the revision we will define and report comparisons against standard baselines (local-only, MEC-only without security, random offloading), add statistical significance tests, and include sensitivity analysis on the security-model parameters to demonstrate robustness of the energy savings. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation builds model then optimizes independently

full rationale

The paper builds a security overhead model to measure execution times, formulates the offloading problem with security/energy/time constraints, applies GA-based coding for task ordering/location/service selection, and runs experiments on workflow parameters. No equations, self-citations, or steps are shown that reduce a claimed prediction or result to fitted inputs or prior self-work by construction. The central claim rests on the model's accuracy and GA solving, which are presented as independent steps rather than tautological. This is the common case of a self-contained engineering paper whose results are benchmarked against its own model assumptions.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review yields no identifiable free parameters, axioms, or invented entities; the security overhead model and risk probability are referenced but not detailed enough to classify.

pith-pipeline@v0.9.0 · 5764 in / 1061 out tokens · 28472 ms · 2026-05-25T08:45:30.736054+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

57 extracted references · 57 canonical work pages

  1. [1]

    Liu, D.X

    X. Liu, D.X. Wang, D. Yuan , F. Wang, Y. Yang, Workflow temporal verification for monitoring parallel business processes, Journal of Software: Evolution and Process 28 (4) (2016) 286-302

    work page 2016

  2. [2]

    T. Q. Dinh, J. Tang, Q. D. La, Offloading in mobile edge computing: task allocation and computational frequency scaling, IEEE Transactions on Communications 65 (8) (2017) 3571- 3584

    work page 2017

  3. [3]

    S. Guo, B. Xiao, Y. Yang, Energy -efficient dynamic of floading and resource scheduling in mobile cloud computing, in: IEEE International Conference on C omputer Communications, 2016, pp. 1 -9

    work page 2016

  4. [4]

    Zhang, J

    F. Zhang, J. Ge, Z. Li, A load -aware resource allocation and task scheduling for the emerging cloudlet system, Future Generation Computer Systems 87 (2018) 438- 456

    work page 2018

  5. [5]

    Satyanarayanan, The emergence of e dge computing, Computer 50 (1) (2017) 30- 39

    M. Satyanarayanan, The emergence of e dge computing, Computer 50 (1) (2017) 30- 39

    work page 2017

  6. [6]

    Y.Y Mao, C.S. You, J. Zhang, K.B. Huang, K.B. Letaief, A survey on mobile edge computing: the communication perspective, IEEE Communication Surveys and Tutorials 19 (4) (2017) 2322- 2358

    work page 2017

  7. [7]

    J. Shen, A. Varbanescu, Y. Lu, Workload partitioning for accelerating applications on heterogeneous platforms, IEEE Transactions on Parallel & Distributed Systems 27 (9) (2016) 2766- 2780

    work page 2016

  8. [8]

    Saty anarayanan, P

    M. Saty anarayanan, P. Bahl, N. Davies, The case for VM -based cloudlets in mobile computing, IEEE Pervasive Computing 8 (4) (2009) 14-23

    work page 2009

  9. [9]

    P. Mach, Z. Becvar, Mobile edge computing: a survey on architecture and computation offloading, IEEE Communications Surveys & Tutorials 19 (3) (2017) 1628- 1656

    work page 2017

  10. [10]

    C. F. Liu, M. Bennis, H. V. Poor, Latency and reliability -aware task offloading and resource allocation for mobile edge computing, in: IEEE GLOBECOM Workshops 2017

    work page 2017

  11. [11]

    L.F. Zeng, B. Veeravalli, X.R. Li, SABA: a security -aware and budget -aware workflow scheduling strategy in clouds, Journal of Parallel and Distributed Computing, 75 (2015) 141- 151

    work page 2015

  12. [12]

    Chang, The business intelligence as a service in the cloud, Future Generation Computer Systems 37 (2014) 512- 534

    V. Chang, The business intelligence as a service in the cloud, Future Generation Computer Systems 37 (2014) 512- 534

    work page 2014

  13. [13]

    Song, Hans -Arno Jacobsen: Static and Dyna mic Process Change

    W. Song, Hans -Arno Jacobsen: Static and Dyna mic Process Change. IEEE Transaction on Services Computing 11(1) (2018) 215-231

    work page 2018

  14. [14]

    Chang, R.J

    V. Chang, R.J. Walters, G. B. Wills, Organisational sustainability modelling -an emerging service and analytics model fo r evaluating cloud computing adoption with two case studies, International Journal of Information Management 36 (1) (2016) 167-179

    work page 2016

  15. [15]

    Chang, Y.H

    V. Chang, Y.H. Kuo, M. Ramachandran, Cloud computing adoption framework: a security framework for business clouds, Future Generation Computer Systems 57 (2016) 24- 41

    work page 2016

  16. [16]

    H. Chen, X. Zhu, D. Qiu, Scheduling for workflows with security-sensitive intermediate data by selective tasks duplication in clouds, IEEE Transactions on Parallel and Distributed Systems 28 (9) (2017) 2674- 2688

    work page 2017

  17. [17]

    Z. Li, J. Ge, H. Yang, A security and cost aware scheduling algorithm for heterogeneous tasks of scientific workflow in clouds, Future Generation Computer Systems 65 (2016) 140- 152

    work page 2016

  18. [18]

    OPENi Consortium, Deliverable 2.3 – Security and Privacy Considerations fo r Cloud -based Services and Cloudlets 530 (2015) 26-37

    work page 2015

  19. [19]

    H. Suo, Z. Liu, J. Wan, K. Zhou, Security and privacy in mobile cloud computing, in: International Wireless Communications and Mobile Computing Conference , 2013, pp. 655- 659

    work page 2013

  20. [20]

    Takabi, T

    H. Takabi, T. S. Zargar, D. B. J. Joshi, Mobile cloud computing and its security and privacy challenges, Security Privacy Trust and Resource Management in Mobile and Wireless Communications, (2014)

    work page 2014

  21. [21]

    Stojmenovic, S

    I. Stojmenovic, S. Wen, X. Huang, H. Luan, An overview of fog computing and its se curity issues, Concurrency and Computation: Practice and Experience, Concurrency & Computation Practice & Experience 28 (10) (2016)2991- 3005

    work page 2016

  22. [23]

    S. Yi, Z. Qin, Q. Li, Security and privacy issues of fog computing: a survey, Springer International Publishing, 2015, pp. 685-695

    work page 2015

  23. [24]

    Roman, J

    R. Roman, J . Lopez, M . Mambo, Mobile edge computing, fog et al.: a survey and analysis of security threats and challenges, Future Generation Computer Systems 78 (2018) 680- 698

    work page 2018

  24. [25]

    Shirazi, A

    S.N. Shirazi, A. Gouglidis, A. Farshad, D. Hutchison, The extended cloud: review and analysis of mobile edge c omputing and fog from a security and resilience perspective, IEEE Journal on Selected Areas in Communications 35(2017) 2586 - 2595

    work page 2017

  25. [26]

    Abbas, Y

    N. Abbas, Y. Zhang, A. Taherkordi, T. Skeie, Mobile edge computing: a survey. IEEE Internet of Things Journal 5(1) (2018) 450 – 465

    work page 2018

  26. [27]

    Z. Zhu, G. Zhang, M. Li, X Liu, Evolutionary multi -objective workflow scheduling in cloud, IEEE Transactions on Parallel & Distributed Systems 27(5) (2016)1344- 1357

    work page 2016

  27. [28]

    Rodriguez, R

    M.A. Rodriguez, R. Buyya, Deadline based resource provisioningand scheduling algor ithm for scientific workflows on clouds, Cloud Computing IEEE Transactions on 2(2) (2014) 222- 235

    work page 2014

  28. [29]

    Arabnejad, J .G

    H. Arabnejad, J .G. Barbosa, A budget constrained scheduling algorithm for workflow applications, Journal of Grid Computing 12(4) (2014)665-679

    work page 2014

  29. [30]

    Durillo, R

    J.J. Durillo, R. Prodan, Multi-objective workflow scheduling in Amazon EC2, Cluster Computing 17(2) (2014)169- 189

    work page 2014

  30. [31]

    X. Lin, C. Q. Wu, On scientific workflowscheduling in clouds under budget constraint, in: International Conference on Parallel Processing, 2013, pp.90 -99

    work page 2013

  31. [32]

    Q. Zhu, G. Agrawal, Resource provisioning with budget constraints for adaptive applications in cloud environments, IEEE Computer Society, 2012

    work page 2012

  32. [33]

    W. Liu, S. Deng, W. Du, Security- aware intermediate data placement strategy in scientific cloud workflows, Knowledge & Information Systems 41(2) (2014) 423- 447

    work page 2014

  33. [34]

    Y. Mao, C. You, J. Zhang, K. Huang, KB. Letaief, Mobile edge computing: survey and research outlook, 2017

    work page 2017

  34. [35]

    Durillo, R

    J.J. Durillo, R. Prodan, J.G. Barbosa, Pareto tradeoff scheduling of workflows on federated com mercial clouds, Simulation Modelling Practice & Theory 58 (2015) 95-111

    work page 2015

  35. [36]

    H. M. Fard, R. Prodan, T. Fahringer, A truthful dynamic workflow scheduling mechanism for commercial multicloud environments,IEEE Transactions on Parallel & Distributed Systems 24(6) (2013) 1203-1212

    work page 2013

  36. [37]

    M. Jia, J. Cao, L. Yang, Heuristic offloading of concurrent tasks for computation- intensive applications in mobile cloud computing, in: INFOCOM Workshops, 2014, pp.352-357

    work page 2014

  37. [38]

    Y. H. Kao, B. Krishnamachari, M. R. Ra, B. Fan, Hermes: Latency optimal task assignment for resource -constrained mobile computing, IEEE Transactions on Mobile Computing, 16(11) (2017) 3056-3069

    work page 2017

  38. [39]

    Muñoz, A

    O. Muñoz, A. Pascual -Iserte, J. Vidal, Optimization of radio and computational resources for energy efficiency in latency-constrained application offloading, IEEE Transactions on Vehicular Technology 64(10) (2015) 4738-4755

    work page 2015

  39. [40]

    C. You, K. Huang, H. Chae, B.H. Kim, Energy -efficient resource allocation for mobile -edge computation offloading, IEEE Transactions on Wireless Communicatio ns 16(3) (2016) 1397-1411

    work page 2016

  40. [41]

    Kumar, J

    K. Kumar, J. Liu, Y.H. Lu, A survey of computation offloading for mobile s ystems, Mobile Networks and Applications 18(1) (2013) 129-140

    work page 2013

  41. [42]

    Y. Wang, M. Sheng, X. Wang, L. wang, J.D. Li, Mobile -edge computing: partial computation offloading using dynamic voltage scaling, IEEE Transactions on Communications 64(10) (2016) 4268 -4282

    work page 2016

  42. [43]

    Khalili, O

    S. Khalili, O. Simeone, Inter -layer per -mobile optimization of cloud mobile computing: a message -passing approach, transactions on emerging telecommunications t echnologies 27(6) (2016) 814-827

    work page 2016

  43. [44]

    S.T. Hong, H. Kim, QoE -aware computation offloading scheduling to capture energy -latency tradeoff in mobile c louds, in: IEEE International Conference on Sensing, Communication, and Networking, 2016, pp.1 -9

    work page 2016

  44. [45]

    Future Generation Computer Systems

    J. Kwak, Y. Kim, J. Lee, DREAM: dynamic r esource and task allocation for energy minimization in mobile cloud This paper appears in the journal “Future Generation Computer Systems”. The published version is available at https://doi.org/10.1016/j.future.2019.03.011 Page 30 of 30 systems, IEEE Journal on Selected Areas in Communications 33(12) (2015) 2510-2523

    work page doi:10.1016/j.future.2019.03.011 2019

  45. [46]

    Jiang, S

    Z. Jiang, S. Mao, E nergy delay tradeoff in cloud offloading for multi -core mobile d evices, IEEE Access, 3 (2017) 2306-2316

    work page 2017

  46. [47]

    Stojmenovic, S

    I. Stojmenovic, S. Wen, X. Huang, An overview of fog computing and its security i ssues, Concurrency and Computation Practice and Experience, 28(10) (2016) 2991- 3005

    work page 2016

  47. [48]

    K. Lee, D. Kim, D. Ha, U. Rajput, H. Oh, On security and privacy issues of fog computing supported internet of things environment, in: International Conference on the Network of the Future, 2015, pp.1- 3

    work page 2015

  48. [49]

    S. Yi, Z. Qin, Q. Li, Security and privacy issues of fog computing: a s urvey, in: International Conference on Wireless Algorithms, Systems, and Applications, 2015, pp.685- 695

    work page 2015

  49. [50]

    T. Xie, X. Qin, Scheduling security -critical real -time applications on c lusters, IEEE Transactions on Computers, 55(7) (2006) 864-879

    work page 2006

  50. [51]

    T. Xie, X. Qin, Security -aware resource allocation for real -time parallel jobs on homogeneous and heterogeneous clusters, IEEE Transactions on Parallel and Distributed Systems 19 (5) (2007) 682- 697

    work page 2007

  51. [52]

    T. Xie, X. Qin, Performance evaluation of a new scheduling algorithm for distributed systems with security heterogeneity, Journal of Parallel and Distributed Computing 67 (10) (2007) 1067- 1081

    work page 2007

  52. [53]

    X. Tang, K. Li, Z. Zeng, A novel security-driven scheduling algorithm for precedence-constrained tasks in heterogeneous distributed systems, IEEE Transactions on Computers 60 (7) 2011 1017- 1029

    work page 2011

  53. [54]

    Y. Jia, R. Buyya, K. T. Chen, Cost -based scheduling of scientific workflow application on utility grids, in: International Conference on E-Science and Grid Computing, 2005, pp. 140- 147

    work page 2005

  54. [55]

    Deb, An efficient constraint handling method for genetic algorithms, Computer Methods in Applied Mechanics and Engineering, 186 (2) (2000) 311-338

    K. Deb, An efficient constraint handling method for genetic algorithms, Computer Methods in Applied Mechanics and Engineering, 186 (2) (2000) 311-338

    work page 2000

  55. [56]

    Miettinen, J

    A.P. Miettinen, J. K. Nurminen , Energy efficiency of mobile clients in cloud computing, in: Usenix Conference on Hot Topics in Cloud Computing, 2010, pp. 4 -4

    work page 2010

  56. [57]

    Y. Xiao, P. Savolainen, A. Karppanen, Practical power modeling of data transmission over 802.11g for wireless applications, in : International Conference on Energy- Efficient Computing and Networking, 2010, pp. 75- 84

    work page 2010

  57. [58]

    S. Deng, L. Huang, J. Taheri, Computation offloading for service workflow in mobile cloud computing, IEEE Transactions on Parallel and Distributed Systems 26 (12) (2015) 3317- 3329

    work page 2015