Searcharxiv⌕ Search

arXiv subjects

Luis G. Jaimes

Publications and source records attributed to Luis G. Jaimes.

2 recordsLinked to original sources

Coverage-Aware Routing with Approximate Equilibrium Guarantees for Location-Diversity Vehicular Crowdsensing

Vehicular crowdsensing uses the sensors of everyday vehicles to monitor cities, but traffic concentrates on few roads, leaving much of the network unsensed. Location-diversity incentives pay vehicles more to travel where few others go, but our earlier mechanism sets how far each vehicle deviates without optimizing collective coverage in route selection. We add this step in two stages. First, a non-cooperative game with diversity-weighted rewards yields each vehicle's equilibrium deviation. Second, the platform recommends to each vehicle a feasible route whose deviation is within a tolerance of this value, chosen to improve coverage. The coverage gain is monotone submodular, so a greedy router with local search attains at least half of the optimal gain over generated candidates. If every active vehicle has a candidate within a tolerance that is small relative to the aggregate deviation, the recommended routes form an $\varepsilon$-Nash equilibrium, with $\varepsilon$ first order in the tolerance, or second order under a stronger condition. On London and Monaco road networks, the router achieves 99.4% and 98.9% of the optimal reduction in the coverage penalty on small instances and exceeds closest-length selection by up to 27.9 points. Under heterogeneous costs, uniform deviation needs compensation averaging 42% of the budget to give every vehicle nonnegative utility; the equilibrium targets need almost none. They also yield more coverage per unit of added travel in most settings and up to 22.6 more points at small budgets, an advantage that depends on placement and reverses at large budgets, where detour limits bind.

cs.GT↗

MA-IDS: Multi-Agent RAG Framework for IoT Network Intrusion Detection with an Experience Library

Network Intrusion Detection Systems (NIDS) face important limitations. Signature-based methods are effective for known attack patterns, but they struggle to detect zero-day attacks and often miss modified variants of previously known attacks, while many machine learning approaches offer limited interpretability. These challenges become even more severe in IoT environments because of resource constraints and heterogeneous protocols. To address these issues, we propose MA-IDS, a Multi-Agent Intrusion Detection System that combines Large Language Models (LLMs) with Retrieval Augmented Generation (RAG) for reasoning-driven intrusion detection. The proposed framework grounds LLM reasoning through a persistent, self-building Experience Library. Two specialized agents collaborate through a FAISS-based vector database: a Traffic Classification Agent that retrieves past error rules before each inference, and an Error Analysis Agent that converts misclassifications into human-readable detection rules stored for future retrieval, enabling continual learning through external knowledge accumulation, without modifying the underlying language model. Evaluated on NF-BoT-IoT and NF-ToN-IoT benchmark datasets, MA-IDS achieves Macro F1-Scores of 89.75% and 85.22%, improving over zero-shot baselines of 17% and 4.96% by more than 72 and 80 percentage points. These results are competitive with SVM while providing rule-level explanations for every classification decision, demonstrating that retrieval-augmented reasoning offers a principled path toward explainable, self-improving intrusion detection for IoT networks.

cs.CR↗