A systematic literature review of eXplainable Artificial Intelligence within the Intelligent and Secure SD-WAN (ISD-WAN) framework and suggests a transition toward a multi-tiered interpretability roadmap, where the depth of the explanation is calibrated to the plane’s processing budget.
Abstract
The paradigm shift toward AI-driven autonomous network orchestration has precipitated a critical strategic vulnerability: the paradox of opaque autonomy. In mission-critical defense environments, the deployment of opaque models for intrusion detection and traffic management poses a severe risk to national security and decision-making accountability. This paper presents a systematic literature review (SLR) of eXplainable Artificial Intelligence (XAI) within the Intelligent and Secure SD-WAN (ISD-WAN) framework, adhering to the PRISMA 2020 guidelines. Through a rigorous analysis of thirty-two primary studies (2020-2026), we identified an architectural transition from post-hoc, management-plane explanations toward intrinsic, real-time interpretability within control and data planes. Our synthesis characterizes a fundamental trilemma between security enforcement, network performance, and computational overhead, highlighting the pivotal role of neuro-symbolic AI and blockchain as anchors for auditability and non-repudiation. We propose a multi-tiered interpretability roadmap thatAn analysis of the surveyed literature suggests a transition toward a multi-tiered interpretability roadmap, where the depth of the explanation is calibrated to the plane’s processing budget, whitch empowers sovereign entities to exercise verifiable control over autonomous information flows. By bridging the gap between algorithmic performance and strategic governance, this study establishes a structured survey and conceptual integration of emerging research framework for resilient, transparent, and technologically sovereign network infrastructures.
As artificial intelligence systems transition from task-specific tools to autonomous agents capable of complex decision-making, traditional external oversight mechanisms become inadequate for ensuring safety, security, and alignment. This paper introduces a governance and security-by-design framework that embeds responsibility mechanisms directly into agentic AI architectures, enabling continuous self-monitoring and alignment verification through multi-agent governance systems. We demonstrate that external governance approaches fail to scale with system autonomy, creating temporal gaps between assessment and deployment that enable ungovernable behaviors. Through mathematical modeling using stochastic differential equations, we formalize how competing objectives in agentic systems create systematic interference patterns that degrade safety properties. Our empirical validation across 800 experiments reveals three critical failure modes:
(1) systematic security vulnerabilities from AI-generated code, with efficiency-focused prompting introducing memory safety issues in 42.7% of cases, while security-focused prompting paradoxically creates cryptographic vulnerabilities in 21.1% of cases;
(2) iterative degradation, where security vulnerabilities increase by 37.6% after just five feedback iterations; and
(3) knowledge dilution, where domain expertise degrades by 47% as irrelevant context accumulates.
Our multi-agent governance and security architecture, validated through industry partnerships, achieves a 40% reduction in post-deployment safety incidents while maintaining operational capability. These findings establish that safe, secure, and aligned agentic systems require architectural integration of governance mechanisms that address the dynamic, multi-objective nature of autonomous AI systems.
Unknown authors· Proceedings of IASEAI Confer...· 0 citations
Mobile network operators are increasingly exploring the use of artificial intelligence (AI) to automate complex network tasks, such as cell selection and mobility management. A fundamental problem arises: there is currently no way to verify that an AI function is making the right decisions or for the right reasons, rather than arriving at correct-looking answers through unreliable shortcuts. In safety-critical and resilience-focused infrastructure, this lack of transparency poses a significant challenge to the widespread adoption of AI technologies in wireless networks. In this paper, we propose a mechanical auditing approach: inspecting a function's internal representations and checking them against machine-verifiable 3GPP specifications. Specifically, we set out a general three-step auditing principle that locates protocol-relevant features, verifies their causal role, and diagnoses how adaptation reshapes their use, grounding it throughout publicly available interpretability and telecommunications research. We present an audit-native network architecture in which a dedicated verification agent continuously checks the reasoning of AI functions in networks, supporting both predeployment certification and runtime auditing. We also discuss how it could be realised, the data and benchmarks, as well as the open challenges that remain before mechanistic auditing can enter telecommunications practice and standardisation.
: Artificial Intelligence (AI) is a key driver of digital transformation across sectors. However, its rapid adoption introduces significant challenges in governance, security, and accountability. Modern AI systems, particularly generative and adaptive models, exhibit non-deterministic behavior, evolving data dependencies, and distributed ownership. These characteristics limit the effectiveness of traditional threat modeling approaches. At the same time, existing governance frameworks treat accountability primarily as a managerial concern and do not integrate it into technical threat modeling processes. This disconnect leads to fragmented oversight, unclear role ownership, and increased security and compliance risks across the AI lifecycle. To address this gap, this paper proposes a lifecycle-aware threat modeling framework for Secure and Trustworthy AI that embeds RACI (Responsible, Accountable, Consulted, Informed) roles into each stage of the threat modeling process. By linking technical threat analysis with explicit accountability, the framework transforms governance into an operational security mechanism. It enables systematic identification of AI-specific risks while ensuring trace-able decision-making and clear risk ownership. The framework further extends to distributed AI ecosystems (RACI+X) by incorporating external actors into the accountability structure. Overall, the approach strengthens resilience against evolving risks and supports secure, transparent, and accountable AI deployment.
Faiza Tahir, Ubaid Ullah, Eric Bodden· International Conference on...· 0 citations
Aim: This study aimed to design, implement, and empirically evaluate an agentic AI framework that improves the reliability, governance, security, and cost efficiency of enterprise Azure data platforms. The framework was intended to move operations from reactive, manual incident handling to policy-constrained automated monitoring and remediation, while preserving auditability, least privilege, and human oversight for high-risk actions. Specifically, the study sought to determine whether bounded agentic control could reduce operational toil, improve pipeline success and recovery times, strengthen security-governance posture, and lower unit costs without violating service-level or compliance constraints.
Methods: We propose an agentic AI framework that (1) continuously telemetries pipeline runs, data-quality checks, lineage, and security posture; (2) retrieval-augments reasoning on operational knowledge (tickets, runbooks, KQL logs, IaC diffs); (3) policy-constrained action execution (RBAC, approvals, change windows, least privilege) to remediate failures, enforce baselines, and optimize resources; and (4) post-action validation to confirm recovery and prevent regressions. The system was built on Azure OpenAI and Azure Databricks, Data Factory, and Microsoft Fabric and tested with an enterprise deployment, a historical incident replay, and an A/B test against standard on-call procedures.
Results: Manual interventions decreased by 65% across workloads, pipeline success rate increased from 91% to >97%, and annualized savings approached USD $1M, with better security-governance scores and lower cost per successful run. Results suggest that policy-gated autonomy lowers mean time to resolve (MTTR) and incident recurrence.
Conclusion: The study supports the use of bounded, auditable agentic control for recurring operational failure modes.
Recommendation: Future work should strengthen robustness guarantees, standardize multi-objective evaluation, and assess portability beyond Azure.
VenkateswaraReddy Gudise· American Journal of Technolo...· 0 citations
Blockchain and artificial intelligence (AI) are converging into a single infrastructural layer for securing data sharing, model integrity, and autonomous decision-making across distributed systems. This paper presents a meta-synthesis that draws together four constituent studies covering adversarial machine learning, AI-powered anomaly detection in cloud environments, automated vulnerability patching by multi-agent large language model (LLM) pipelines, and the broader landscape of securing AI systems across their lifecycle and situates their findings within the emerging literature on blockchain-enabled AI and autonomous AI agents. Each constituent study addresses a distinct point of failure in modern AI-driven security operations: the integrity of training data and model behavior, the reliability of real-time monitoring, and the trustworthiness of automated code remediation. We argue that blockchain's properties of immutability, decentralized consensus, and verifiable provenance directly address a gap common to all three: the difficulty of establishing trust in data, models, and autonomous agents that operate without a central authority. Building on real-world research on blockchain-secured data sharing, federated learning, and multi-agent coordination, we propose a layered reference architecture that couples adversarially hardened models, blockchain-anchored data provenance, AI-driven anomaly detection, and smart-contract-governed multi-agent remediation. We conclude by identifying open problems in scalability, privacy-transparency trade-offs, and the governance of autonomous agents that must be resolved before such integrated systems can be trusted in production-critical environments.
Harsh Verma· International Journal of Sci...· 0 citations
LATTICE (Layered Agentic Triad Topology for Intelligent Coordinated Execution), a governance-first architecture that reframes the authorization question from “do the authors trust this AI?” to “do they trust this architecture?”
Elias Calboreanu· Frontiers in Artificial Inte...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
