Security Operations Centers (SOCs) increasingly rely on Security Orchestration, Automation, and Response (SOAR) platforms to manage high-volume alerts, enrich telemetry, execute playbooks, and shorten incident-response cycles. However, many deployed SOAR systems remain rule dominated: actions are triggered by static if-then playbooks, threshold scores, and analyst-defined routing logic. Such deterministic automation is auditable and operationally useful for known, repetitive events, but it becomes brittle when adversary behavior shifts, telemetry quality varies, alert streams are noisy, assets have unequal business criticality, and compliance constraints differ across response contexts. This paper proposes an Intelligent Security Operations Automation Algorithm (ISOAA) for AI-enabled SOAR. The algorithm integrates probabilistic alert risk scoring, event-graph representation, constrained response optimization, governance-risk-compliance (GRC) gating, human-in-the-loop validation, and feedback-based policy improvement. The mathematical core models each alert as a feature-bearing security object, transforms heterogeneous telemetry into a state representation, estimates actionable incident probability, and selects response actions by maximizing expected security utility subject to operational cost, false-positive loss, and compliance penalty. A rule-based SOAR baseline, an ML-assisted triage baseline, and a reinforcement-learning cyber-response baseline are used for comparative analysis. Controlled benchmark results indicate that ISOAA achieves lower mean time to detect, lower mean time to respond, higher containment success, improved precision and recall, reduced false-positive automation, and lower compliance-breach rate than rule-based SOAR. The paper contributes a defensible mathematical architecture for intelligent SOC automation and offers practical deployment recommendations for risk-aware, auditable, and GRC-constrained response orchestration.
Ikenna Mbuko, O. Ijiga, L. Enyejo· International Journal of Eng...· 0 citations
Generative artificial intelligence systems increasingly operate as autonomous agents capable of retrieving external
information, accessing confidential resources, invoking application programming interfaces, and executing consequential
actions. These capabilities introduce substantial security risks because malicious instructions embedded in user prompts,
retrieved documents, webpages, emails, tool outputs, or persistent memory may alter an agent’s intended behaviour.
Conventional keyword filters, standalone prompt classifiers, and static access-control mechanisms provide limited
protection against semantically obfuscated attacks, multi-stage data exfiltration, manipulated tool arguments, and attacks
that remain within formally permitted privileges. This paper develops SecurePromptTrace, a novel runtime security
algorithm for detecting and controlling prompt injection, sensitive-data exfiltration, and tool misuse in generative artificial
intelligence systems.
SecurePromptTrace constructs a Dynamic Prompt Provenance Graph that represents trusted instructions, untrusted
content, model-generated plans, retrieved data, confidential variables, tool calls, tool arguments, and execution outcomes as
provenance-labelled nodes and causal edges. A relation-aware graph attention network analyses instruction dependencies
and identifies conflicts between the authenticated user objective and instructions originating from untrusted sources. The
graph model is integrated with a DeBERTa-v3 semantic injection classifier, confidential-data taint propagation, cross-layer
intent alignment, tool-capability compatibility analysis, and adaptive policy enforcement. A composite threat score combines
semantic injection probability, provenance conflict, sensitive-data flow, tool-privilege mismatch, execution-sequence
deviation, and predictive uncertainty. According to the calculated risk, the algorithm permits, sanitises, replans, isolates,
requests approval for, or blocks an operation.
The evaluation framework covers direct and indirect prompt injection, encoded and multilingual attacks, contextwindow attacks, memory poisoning, cross-tool exfiltration, parameter substitution, privilege chaining, and unauthorised
tool execution. SecurePromptTrace is compared with Aho–Corasick keyword filtering, regular-expression filtering, a
standalone DeBERTa-v3 classifier, PromptShield-style detection, role-based access control, attribute-based access control,
and combined static guardrails. Performance is assessed using macro-F1 score, precision, recall, AUROC, AUPRC, attack
success rate, data-exfiltration prevention rate, tool-misuse prevention rate, false-positive rate, task-utility retention,
computational latency, and memory overhead. Comparative bar charts, ROC and precision–recall curves, confusion
matrices, risk-score distributions, ablation graphs, and security–latency Pareto plots are used to demonstrate performance
differences. The central hypothesis is that provenance-aware semantic and behavioural tracing will produce significantly
lower attack-success and exfiltration rates than content-only or permission-only defenses while preserving legitimate task
completion. Statistical superiority will be established through confidence intervals, McNemar tests, bootstrap comparisons,
and effect-size analysis.
Praise Elojo Attah, L. Enyejo· International Journal of Inn...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
