Mitigating Evasion Attacks in Fog Computing Resource Provisioning Through Proactive Hardening

Younes Salmi; Hanna Bogucka

cs.CRMar 26, 2026

Mitigating Evasion Attacks in Fog Computing Resource Provisioning Through Proactive Hardening

Authors: Younes Salmi, Hanna Bogucka

Organizations: Institute of Radiocommunications, Poznan University of Technology, Poznań, Poland

Abstract

This paper investigates the susceptibility to model integrity attacks that overload virtual machines assigned by the k-means algorithm used for resource provisioning in fog networks. The considered k-means algorithm runs two phases iteratively: offline clustering to form clusters of requested workload and online classification of new incoming requests into offline-created clusters. First, we consider an evasion attack against the classifier in the online phase. A threat actor launches an exploratory attack using query-based reverse engineering to discover the Machine Learning (ML) model (the clustering scheme). Then, a passive causative (evasion) attack is triggered in the offline phase. To defend the model, we suggest a proactive method using adversarial training to introduce attack robustness into the classifier. Our results show that our mitigation technique effectively maintains the stability of the resource provisioning system against attacks.

Figures & tables

Fig. 2: Mapping of the considered attacks to Attack-MITRE-ATLAS

Parameter	Value	Parameter	Value
$l$	3	$\|\mathcal{Q}_{ij}\|$	10
$M$	[100, 1000]	$\zeta_{1}$	9/10
$M^{\prime}$	[100, 1000]	$\zeta_{2}$	1/10
${\alpha_{i}}/{\tilde{\alpha_{i}}}$	[1, 3]	$\eta_{\mathrm{ex}},\eta_{\mathrm{ev}},\eta_{\mathrm{at}}$	1/1000
$\tau_{\mathrm{ex}},\tau_{\mathrm{ev}}$	1/2	$\epsilon_{\mathrm{ev}},\epsilon_{\mathrm{at}}$	4/100
$\iota$	1/1000	PER range	[ 27 ]

TABLE I: Simulation Parameters

Fig. 3: Simulation results for correct resource provisioning

Fig. 4: Attacked vs. protected ML-based provisioning simulation results

Adversarial Attacks

Adversarial attacks exploit crafted inputs, poisoned data, or system interactions to manipulate AI predictions, behavior, privacy, or reliability.

See all 447 papers

KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks
Aug 21, 2026Mohammad Meymani, Roozbeh Razavi-FarAdversarial Robustness Kolmogorov-Arnold Networks
Trustworthy and Secure AI (TSAI) Lab, Faculty of Computer Science, University of New Brunswick, Fredericton, Canada
Enabling Adversarial Robustness in AI Models through Kubeflow MLOps
May 14, 2026Stavros Bouras, Ioannis Korontanis, Antonios Makris +1Adversarial Attacks Adversarial Robustness
School of Electrical and Computer Engineering, National Technical University of Athens, Greece · Department of Informatics and Telematics, Harokopio University of Athens, Greece
ResAware: Cross-Environment Website Fingerprinting via Resource-Privileged Distillation
Jun 16, 2026Chongru Fan, Wei Wang, Wentao Huang +5Encrypted Network Traffic Analysis Cybersecurity
Beijing University of Posts and Telecommunications Beijing, China · Zhongguancun Laboratory Beijing, China

Aug 21, 2026J/K move · Enter open · S save

KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks

Mohammad Meymani, Roozbeh Razavi-Far

Trustworthy and Secure AI (TSAI) Lab, Faculty of Computer Science, University of New Brunswick, Fredericton, Canada

Adversarial Robustness Kolmogorov-Arnold Networks Certified Robustness Adversarial Attacks

Open paper AskPDF arXiv

While machine learning models have demonstrated strong performance in many domains, these models have shown profound vulnerabilities when they are exposed to adversarial threats. While adversarial attacks fall into various categories, the most prominent category in research studies is evasion. In evasion attacks, the adversary generates perturbed versions of samples, which might not be observable by human eyes. These samples generally fool the machine learning models with high confidence. This phenomenon poses a significant security violation against machine learning models. In this paper, we investigate the certified and empirical robustness of various Kolmogorov-Arnold network architectures against strong evasion attacks. At first, we provide the mathematical foundations for randomized smoothing and interval bound propagation, and report the

\ell_2

-certified robustness of the models under randomized smoothing. After that, we systematically evaluate the robustness of various defended and undefended KAN models under FGSM, PGD, and C&W attacks in order to find out the optimal defense strategies and architectures.

Abstract

Adversarial Attacks

Explore similar work

KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks

Enabling Adversarial Robustness in AI Models through Kubeflow MLOps

ResAware: Cross-Environment Website Fingerprinting via Resource-Privileged Distillation