arXiv subjects

Dingde Jiang

Publications and source records attributed to Dingde Jiang.

5 recordsLinked to original sources

arXiv2025

A Network Arena for Benchmarking AI Agents on Network Troubleshooting

Agentic systems, powered by Large Language Models (LLMs), assist network engineers with network configuration synthesis and network troubleshooting tasks. For network troubleshooting, progress is hindered by the absence of standardized and accessible benchmarks for evaluating LLM agents in dynamic network settings at low operational effort. We present NIKA, the largest public benchmark to date for LLM-driven network incident diagnosis and troubleshooting. NIKA targets both domain experts and especially AI researchers alike, providing zero-effort replay of real-world network scenarios, and establishing well-defined agent-network interfaces for quick agent prototyping. NIKA comprises hundreds of curated network incidents, spanning five network scenarios, from data centers to ISP networks, and covers 54 representative network issues. Lastly, NIKA is modular and extensible by design, offering APIs to facilitate the integration of new network scenarios and failure cases. We evaluate state-of-the-art LLM agents on NIKA and find that while larger models succeed more often in detecting network issues, they still struggle to localize faults and identify root causes. NIKA is open-source and available to the community: https://github.com/sands-lab/nika.

cs.NI↗

arXiv2025

ChamaleoNet: Programmable Passive Probe for Enhanced Visibility on Erroneous Traffic

Traffic visibility remains a key component for management and security operations. Observing erroneous traffic, i.e., unanswered requests or error messages, is fundamental to detecting misconfiguration, temporary failures or attacks. ChamaleoNet transforms any production network into a transparent monitor to let administrators collect such erroneous traffic. ChamaleoNet is programmed to ignore well-formed traffic and record only erroneous packets, including those generated by misconfigured or infected internal hosts, and those sent by external actors that scan for services. Engineering such a system poses several challenges, from scalability to privacy. Leveraging the Software-Defined Networking (SDN) paradigm, ChamaleoNet processes the humongous amount of traffic flowing through the network border and focuses on erroneous packets only, lowering the pressure on the collection system. Moreover, it offers traffic anonymisation to conform to privacy regulations. ChamaleoNet enables the seamless integration with active deceptive systems like honeypots that can impersonate hosts/ports/services and engage with senders. In an operational scenario, we show that the SDN in-hardware filtering reduces the traffic to the controller by 90%, resulting in a scalable solution, which we offer as open source. Simple statistical analytics unveil the precious information carried by erroneous traffic. We discover internal misconfigured and infected hosts, identify temporary failures, and show enhanced visibility on attackers' scanning activities that look for vulnerable services.

cs.CR↗

arXiv2025

Towards a Playground to Democratize Experimentation and Benchmarking of AI Agents for Network Troubleshooting

Recent research has demonstrated the effectiveness of Artificial Intelligence (AI), and more specifically, Large Language Models (LLMs), in supporting network configuration synthesis and automating network diagnosis tasks, among others. In this preliminary work, we restrict our focus to the application of AI agents to network troubleshooting and elaborate on the need for a standardized, reproducible, and open benchmarking platform, where to build and evaluate AI agents with low operational effort.

cs.NI↗

arXiv2021

Wireless Secret Sharing Game between Two Legitimate Users and an Eavesdropper

Wireless secret sharing is crucial to information security in the era of Internet of Things. One method is to utilize the effect of the randomness of the wireless channel in the data link layer to generate the common secret between two legitimate users Alice and Bob. This paper studies this secret sharing mechanism from the perspective of game theory. In particular, we formulate a non-cooperative zero-sum game between the legitimate users and an eavesdropper Eve. In a symmetrical game where Eve has the same probability of successfully receiving a packet from Alice and Bob when the transmission distance is the same, we show that both pure and mixed strategy Nash equilibria exist. In an asymmetric game where Eve has different probabilities of successfully receiving a packet from Alice and Bob, a pure strategy may not exist; in this case, we show how a mixed strategy Nash equilibrium can be found.

cs.NI↗

arXiv2018

Optimal On-Off Control for a Class of Discrete Event Systems with Real-Time Constraints

This paper studies an optimal ON-OFF control problem for a class of discrete event systems with real-time constraints. Our goal is to minimize the overall costs, including the operating cost and the wake-up cost, while still guaranteeing the deadline of each individual task. In particular, we consider the homogeneous case in which it takes the same amount of time to serve each task and each task needs to be served by d seconds upon arrival. The problem involves two subproblems: (i) finding the best time to wake up the system and (ii) finding the best time to let the system go to sleep. We study the two subproblems in both off-line and on-line settings. In the off-line case that all task information is known a priori, we combine sample path analysis and dynamic programming to come up with the optimal solution. In the on-line scenario where future task information is completely unknown, we show that the optimal time to wake up the system can be obtained without relying on future task arrivals. We also perform competitive analysis for on-line control and derive the competitive ratios for both deterministic and random controllers.

math.OC↗