KuTIE (Kubernetes Topology Intelligence Engine), which builds a live cluster context from Istio call edges, Trivy KSPM findings, and the service-account bindings a workload reads, and conditions LLM patch generation on it, and improves remediation of topology-dependent findings well beyond scanner-only context.
Abstract
Kubernetes is central to the cloud-native ecosystem, orchestrating containerised workloads. Recent work suggests that large language models (LLMs) can automate cluster security remediation, generating configuration patches from Kubernetes Security Posture Management (KSPM) findings without human authoring. Such systems, however, prompt the model with each finding in isolation from the live service call graph, assuming general hardening knowledge suffices. This assumption breaks down whenever a patch must preserve a runtime service dependency invisible to the model: an otherwise compliant fix then carries a destructive functional blast radius, crashing downstream callers or silently severing call edges across the cluster. Whether live cluster context improves patch correctness has not been measured under controlled conditions across multiple dependency classes. We introduce KuTIE (Kubernetes Topology Intelligence Engine), which builds a live cluster context from Istio call edges, Trivy KSPM findings, and the service-account bindings a workload reads, and conditions LLM patch generation on it. It is evaluated on VulnCare, a purpose-built 36-deployment, four-namespace healthcare cluster with 31 injectable findings across seven dependency classes, each labelled by topology dependence against cluster ground truth. Across 248 trials, topology context raises topology-dependent patch correctness from 11.1% to 78.0% ($\Delta = 0.669$), a gap that holds for every model and for six of seven classes, from credential and network-policy ($\Delta = 0.95$) to role-based access control ($\Delta = 0.31$); a topology-independent control exhibits no such effect ($\Delta = 0.0$), isolating the result from generic prompt enrichment. Supplying the live service-call graph and the service-account bindings it exposes thus improves remediation of topology-dependent findings well beyond scanner-only context.
KubeCap, a framework for Kubernetes capability minimization, is proposed and Evaluation on 10 representative Go-based Kubernetes projects shows an average capability reduction rate of 54.97%, outperforming rapid type analysis and class hierarchy analysis baselines while maintaining practical analysis cost.
Yuhao Liu, Yingnan Zhou, Weijie Liu et al.· 0 citations
The growing complexity of runtime management in containerized clusters makes manual fault debugging time-consuming and costly. Self-healing aims to automate fault detection and recovery. A recent approach is to use large language models (LLMs), but most existing systems rely on large proprietary models with high computational or service costs. This paper investigates the feasibility of using low-parameter, on-premise LLMs for self-healing of containerized applications in Kubernetes clusters. Our proposed prototype leverages prompt chaining by splitting failure management tasks into root cause analysis and auto-remediation prompts, where each prompt is augmented with in-context examples. We allow the LLM to iteratively refine its output based on cluster feedback until remediation execution and recovery are successful. Evaluated on a microservice benchmark system with 15 real-time faults, our prototype achieves 96.67% overall accuracy. Results show that prompt chaining and iterative refinement significantly improve recovery effectiveness, while in-context learning yields limited benefit.
Yann Wiesinger, M. Engelhardt, Roman Laas· SEAMS@ICSE· 0 citations
Migrating microservices across virtual machines (VMs) without knowledge of their runtime communication patterns risks creating cross-VM hotspots and latency spikes that are difficult to predict from static analysis alone. We use extended Berkeley Packet Filter (eBPF) kernel-level network tracing to automatically discover inter-service dependencies at runtime, with no application instrumentation, and use the resulting dependency graph to produce a traffic-aware migration plan ranked by return on investment (ROI). A two-pass process-identifier (PID) to port correlation algorithm recovers the identity of all 20 services in a shared-runtime testbed where processes are otherwise indistinguishable, matching the known ground-truth topology. The system discovers 32 dependency edges from 13,615 network events captured in three minutes, and applies spectral graph clustering with Kernighan-Lin refinement to partition services into VM-coherent groups. In simulation over the discovered graph, our ROI-ranked migration order reduces cumulative cross-VM traffic exposure during the migration window by 27% relative to alphabetical ordering, a deterministic proxy for arbitrary dependency-blind ordering. Collection overhead is mixed: in a controlled A/B test at near-saturation load on a host with two virtual CPUs (vCPUs), throughput fell by only 4.4%, but median (p50) latency rose by 383% and 99th-percentile (p99) latency by 1,050%. We therefore recommend running captures off-peak or on dedicated sampling nodes rather than under production saturation. All results are from a single 20-service testbed that we authored; we make no claim about behavior on production dependency graphs.
Modern services are awash in Application Programming Interfaces (APIs), yet most security pipelines end at pre-deployment testing using fuzzers and scanners. This leaves a run-time gap where payload obfuscation and other evolving request-visible misuse patterns outpace static rules and slow retraining cycles. We present HotPatchCaps, an expert-in-the-loop runtime framework that closes this gap by hot patching expert knowledge into a capsule architecture without retraining. HotPatchCaps fuses Term Frequency–Inverse Document Frequency (TF–IDF) statistics on request tokens with security cues such as parameter names, encodings, and payload substrings, and employs slot-controlled routing to amplify semantically relevant evidence into interpretable capsule activations. New rules arrive as lightweight runtime patches that can be injected on the fly, aligning with operational practice while preserving the generalization of learned models. We evaluated the CSIC 2010 dataset and the ATRDF 2023 dataset in both in-distribution and zero-day settings against classical machine learning (ML) and deep baselines. Experimental results demonstrate that HotPatchCaps consistently improves accuracy and recall at competitive precision and remains robust under label noise and schema drift. By turning expert knowledge into patchable capsule priors, HotPatchCaps provides a practical path from testing to on-call defence for API-centric systems.
Tong Li, Shicheng Wei, Wencheng Yang et al.· IEEE Transactions on Network...· 0 citations
Production data migrations run with write credentials, often while the application they serve continues to handle
traffic, and their worst failure modes concern how they change data rather than whether the code runs. Language model
reviewers are increasingly asked to gate such scripts, with little evidence about their reliability in this setting. This paper
presents MigBench, a benchmark of 300 MongoDB migration scripts in which 100 are correct and 200 each contain
exactly one defect from eight operationally defined categories. The dataset is generated deterministically from a single
seed, and every label is certified by execution: each script runs against a disposable MongoDB replica set under five
behavioral probes covering expected state and scope, repeated execution, a counter race against simulated live traffic,
crash injection with an invariant across collections, and crash injection followed by resume. All 300 labels were confirmed
by behavior before any reviewer ran.
Ahmed F. Mohamed· International Journal of Inn...· 0 citations
Multi-provider LLM gateways reverse proxies that route, load-balance, and rate-limit requests across foundation-model APIs have become critical production infrastructure. Yet the failure modes specific to this architectural layer remain undocumented, scattered across issue trackers and post-mortems with no unifying framework. We introduce \fa{}, a two-axis taxonomy that classifies failures by their \emph{origin layer} (Network/Transport, Streaming/Protocol, State/Session, Model~Behavior, Governance/Cost) and their \emph{detectability} (Loud vs.\ Silent). We populate this taxonomy with five verified catalog entries sourced from public bug reports and first-hand stress testing, each accompanied by a mechanistic root-cause analysis. Three entries include standalone reproduction scripts. Our principal finding is that the most operationally severe failures are \emph{silent}: they return HTTP~200, pass every standard health check, and corrupt application state in ways that require semantic-level observability to detect. Two such silent failures a concurrency race condition causing history loss and a streaming index collision corrupting tool-call payloads were discovered first-hand during \cb{} evaluation campaigns.
