Marco Chiesa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Marco Chiesa has a total of 137 co-authors. Here are the top co-authors by number of shared publications:
- Dejan Kostić
Medical Faculty of the Military Medical Academy, Belgrade, Serbia
11 shared publications - Marco Canini
King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
10 shared publications Michael Schapira
Hebrew University of Jerusalem, Jerusalem 9190401, Israel
8 shared publications- Gerald Q. Maguire
KTH Royal Institute of Technology
7 shared publications - Giuseppe Di Battista
Department of Engineering, Roma Tre University, Rome, Italy
7 shared publications Christoph Dietzel
DE-CIX / MPI for Informatics
6 shared publications
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 184-191
RAG Against the Machine: Zero-Shot Software Vulnerabilities Classification using LLMs
Timely detection and mitigation of software vulnerabilities is essential for maintaining secure systems. While recent research has applied Transformer-based models to automatically identify vulnerabilities from sources such as GitHub issues, these approaches do not classify the detected vulnerabilities. Without systematic classification, it becomes difficult to prioritize issues, link them to remediation strategies, or integrate them into broader security workflows. This paper introduces a novel approach for automated vulnerability categorization using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) within the Common Weakness Enumeration (CWE) framework. We present a RAG-based pipeline for CWE labeling and systematically evaluate multiple retrieval strategies to assess their effectiveness and efficiency. The results demonstrate that our approach achieves competitive performance compared to prior state-of-the-art methods, despite operating entirely in a zero-shot setting without any task-specific training. Moreover, the proposed method enables accurate and cost-effective vulnerability classification, helping to reduce the gap between discovery and remediation in the vulnerability lifecycle. This work highlights the potential of retrieval-driven approaches to enhance the automation, scalability, and practicality of vulnerability management across the software ecosystem.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 184-191
Open AccessRAG Against the Machine: Zero-Shot Software Vulnerabilities Classification using LLMs
Timely detection and mitigation of software vulnerabilities is essential for maintaining secure systems. While recent research has applied Transformer-based models to automatically identify vulnerabilities from sources such as GitHub issues, these approaches do not classify the detected vulnerabilities. Without systematic classification, it becomes difficult to prioritize issues, link them to remediation strategies, or integrate them into broader security workflows. This paper introduces a novel approach for automated vulnerability categorization using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) within the Common Weakness Enumeration (CWE) framework. We present a RAG-based pipeline for CWE labeling and systematically evaluate multiple retrieval strategies to assess their effectiveness and efficiency. The results demonstrate that our approach achieves competitive performance compared to prior state-of-the-art methods, despite operating entirely in a zero-shot setting without any task-specific training. Moreover, the proposed method enables accurate and cost-effective vulnerability classification, helping to reduce the gap between discovery and remediation in the vulnerability lifecycle. This work highlights the potential of retrieval-driven approaches to enhance the automation, scalability, and practicality of vulnerability management across the software ecosystem.
- Open Access
Dissect-and-Restore: AI-based Code Verification with Transient Refactoring
Formal verification is increasingly recognized as a critical foundation for building reliable software systems. However, the need for specialized expertise to write precise specifications, navigate complex proof obligations, and learn annotations often makes verification an order of magnitude more expensive than implementation. While modern AI systems can recognize patterns in mathematical proofs and interpret natural language, effectively integrating them into the formal verification process remains an open challenge. We present Prometheus, a novel AI-assisted system that facilitates automated code verification with current AI capabilities in conjunction with modular software engineering principles (e.g., modular refactoring). Our approach begins by decomposing complex program logic, such as nested loops, into smaller, verifiable components. Once verified, these components are recomposed to construct a proof of the original program. This decomposition-recomposition workflow is non-trivial. Prometheus addresses this by guiding the proof search through structured decomposition of complex lemmas into smaller, verifiable sub-lemmas. When automated tools are insufficient, users can provide lightweight natural language guidance to steer the proof process effectively. Our evaluation demonstrates that transiently applying modular restructuring to the code substantially improves the AI's effectiveness in verifying individual components. This approach successfully verifies 86% of tasks in our curated dataset, compared to 68% for the baseline. Gains are more pronounced with increasing specification complexity, improving from 30% to 69%, and when integrating proof outlines for complex programs, from 25% to 87%.
Open AccessDissect-and-Restore: AI-based Code Verification with Transient Refactoring
Formal verification is increasingly recognized as a critical foundation for building reliable software systems. However, the need for specialized expertise to write precise specifications, navigate complex proof obligations, and learn annotations often makes verification an order of magnitude more expensive than implementation. While modern AI systems can recognize patterns in mathematical proofs and interpret natural language, effectively integrating them into the formal verification process remains an open challenge. We present Prometheus, a novel AI-assisted system that facilitates automated code verification with current AI capabilities in conjunction with modular software engineering principles (e.g., modular refactoring). Our approach begins by decomposing complex program logic, such as nested loops, into smaller, verifiable components. Once verified, these components are recomposed to construct a proof of the original program. This decomposition-recomposition workflow is non-trivial. Prometheus addresses this by guiding the proof search through structured decomposition of complex lemmas into smaller, verifiable sub-lemmas. When automated tools are insufficient, users can provide lightweight natural language guidance to steer the proof process effectively. Our evaluation demonstrates that transiently applying modular restructuring to the code substantially improves the AI's effectiveness in verifying individual components. This approach successfully verifies 86% of tasks in our curated dataset, compared to 68% for the baseline. Gains are more pronounced with increasing specification complexity, improving from 30% to 69%, and when integrating proof outlines for complex programs, from 25% to 87%.
- Open Access
- 22 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 113-119
On the Benefits of Predictable Traffic in Virtual Switches: A Case Study
- 22 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 113-119
Open AccessOn the Benefits of Predictable Traffic in Virtual Switches: A Case Study
- 29 April 2025
- Published by Springer Nature
- p. 301-312
Reducing the Number of Leads for ECG Imaging with Graph Neural Networks and Meaningful Latent Space
- 29 April 2025
- Published by Springer Nature
- p. 301-312
Reducing the Number of Leads for ECG Imaging with Graph Neural Networks and Meaningful Latent Space
- Open Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 132-138
Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 132-138
Open AccessPriority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference
- 8 February 2025
- Published by Springer Nature
- p. 18-32
FMM-Head: Enhancing Autoencoder-Based ECG Anomaly Detection with Prior Knowledge
- 8 February 2025
- Published by Springer Nature
- p. 18-32
FMM-Head: Enhancing Autoencoder-Based ECG Anomaly Detection with Prior Knowledge
- Open Access
- 18 August 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 2 (CoNEXT3) , 1-22
FAJITA: Stateful Packet Processing at 100 Million pps
Data centers increasingly utilize commodity servers to deploy low-latency Network Functions (NFs). However, the emergence of multi-hundred-gigabit-per-second network interface cards (NICs) has drastically increased the performance expected from commodity servers. Additionally, recently introduced systems that store packet payloads in temporary off-CPU locations (e.g., programmable switches, NICs, and RDMA servers) further increase the load on NF servers, making packet processing even more challenging. This paper demonstrates existing bottlenecks and challenges of state-of-the-art stateful packet processing frameworks and proposes a system, called FAJITA, to tackle these challenges & accelerate stateful packet processing on commodity hardware. FAJITA proposes an optimized processing pipeline for stateful network functions to minimize memory accesses and overcome the overheads of accessing shared data structures while ensuring efficient batch processing at every stage of the pipeline. Furthermore, FAJITA provides a performant architecture to deploy high-performance network functions service chains containing stateful elements with different state granularities. FAJITA improves the throughput and latency of high-speed stateful network functions by ~2.43x compared to the most performant state-of-the-art solutions, enabling commodity hardware to process up to ~178 Million 64-B packets per second (pps) using 16 cores.
- 18 August 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 2 (CoNEXT3) , 1-22
Open AccessFAJITA: Stateful Packet Processing at 100 Million pps
Data centers increasingly utilize commodity servers to deploy low-latency Network Functions (NFs). However, the emergence of multi-hundred-gigabit-per-second network interface cards (NICs) has drastically increased the performance expected from commodity servers. Additionally, recently introduced systems that store packet payloads in temporary off-CPU locations (e.g., programmable switches, NICs, and RDMA servers) further increase the load on NF servers, making packet processing even more challenging. This paper demonstrates existing bottlenecks and challenges of state-of-the-art stateful packet processing frameworks and proposes a system, called FAJITA, to tackle these challenges & accelerate stateful packet processing on commodity hardware. FAJITA proposes an optimized processing pipeline for stateful network functions to minimize memory accesses and overcome the overheads of accessing shared data structures while ensuring efficient batch processing at every stage of the pipeline. Furthermore, FAJITA provides a performant architecture to deploy high-performance network functions service chains containing stateful elements with different state granularities. FAJITA improves the throughput and latency of high-speed stateful network functions by ~2.43x compared to the most performant state-of-the-art solutions, enabling commodity hardware to process up to ~178 Million 64-B packets per second (pps) using 16 cores.
- Top Cited PapersOpen Access
- 13 June 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 2 (CoNEXT2) , 1-25
NetConfEval: Can LLMs Facilitate Network Configuration?
This paper explores opportunities to utilize Large Language Models (LLMs) to make network configuration human-friendly, simplifying the configuration of network devices & development of routing algorithms and minimizing errors. We design a set of benchmarks (NetConfEval) to examine the effectiveness of different models in facilitating and automating network configuration. More specifically, we focus on the scenarios where LLMs translate high-level policies, requirements, and descriptions (i.e., specified in natural language) into low-level network configurations & Python code. NetConfEval considers four tasks that could potentially facilitate network configuration, such as (i) generating high-level requirements into a formal specification format, (ii) generating API/function calls from high-level requirements, (iii) developing routing algorithms based on high-level descriptions, and (iv) generating low-level configuration for existing and new protocols based on input documentation. Learning from the results of our study, we propose a set of principles to design LLM-based systems to configure networks. Finally, we present two GPT-4-based prototypes to (i) automatically configure P4-enabled devices from a set of high-level requirements and (ii) integrate LLMs into existing network synthesizers.
- 13 June 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 2 (CoNEXT2) , 1-25
Top Cited PapersOpen AccessNetConfEval: Can LLMs Facilitate Network Configuration?
This paper explores opportunities to utilize Large Language Models (LLMs) to make network configuration human-friendly, simplifying the configuration of network devices & development of routing algorithms and minimizing errors. We design a set of benchmarks (NetConfEval) to examine the effectiveness of different models in facilitating and automating network configuration. More specifically, we focus on the scenarios where LLMs translate high-level policies, requirements, and descriptions (i.e., specified in natural language) into low-level network configurations & Python code. NetConfEval considers four tasks that could potentially facilitate network configuration, such as (i) generating high-level requirements into a formal specification format, (ii) generating API/function calls from high-level requirements, (iii) developing routing algorithms based on high-level descriptions, and (iv) generating low-level configuration for existing and new protocols based on input documentation. Learning from the results of our study, we propose a set of principles to design LLM-based systems to configure networks. Finally, we present two GPT-4-based prototypes to (i) automatically configure P4-enabled devices from a set of high-level requirements and (ii) integrate LLMs into existing network synthesizers.
- Open Access
- 22 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 28-38
Deploying Stateful Network Functions Efficiently using Large Language Models
Stateful network functions are increasingly used in data centers. However, their scalability remains a significant challenge since parallelizing packet processing across multiple cores requires careful configuration t o avoid compromising the application's semantics or performance. This challenge is particularly important when deploying multiple stateful functions on multi-core servers. This paper proposes FlowMage, a system that leverages Large Language Models (LLMs) to perform code analysis and extract essential information from stateful network functions (NFs) prior to their deployment on a server. FlowMage uses this data to find an efficient configuration of an NF chain that maximizes performance while preserving the semantics of the NF chain. Our evaluation shows that, utilizing GPT-4, FlowMage is able to find and apply optimized configuration when deploying stateful NFs chain on a server, resulting in significant p erformance improvement (up to 11×) in comparison to the default configuration of the system.
- 22 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 28-38
Open AccessDeploying Stateful Network Functions Efficiently using Large Language Models
Stateful network functions are increasingly used in data centers. However, their scalability remains a significant challenge since parallelizing packet processing across multiple cores requires careful configuration t o avoid compromising the application's semantics or performance. This challenge is particularly important when deploying multiple stateful functions on multi-core servers. This paper proposes FlowMage, a system that leverages Large Language Models (LLMs) to perform code analysis and extract essential information from stateful network functions (NFs) prior to their deployment on a server. FlowMage uses this data to find an efficient configuration of an NF chain that maximizes performance while preserving the semantics of the NF chain. Our evaluation shows that, utilizing GPT-4, FlowMage is able to find and apply optimized configuration when deploying stateful NFs chain on a server, resulting in significant p erformance improvement (up to 11×) in comparison to the default configuration of the system.
- Open Access
- 27 November 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 1 (CoNEXT3) , 1-23
Millions of Low-latency State Insertions on ASIC Switches
Key-value data structures are an essential component of today's stateful packet processors such as load balancers, packet schedulers, and more. Realizing key-value data structures entirely in the data-plane of an ASIC switch would bring enormous energy savings. Yet, today's implementations are ill-suited for stateful packet processing as they support only a limited amount of flow-state insertions per second into these data structures. In this paper, we present SWITCHAROO, a mechanism for realizing key-value data structures on programmable ASIC switches that supports both high-frequency insertions and fast lookups entirely in the data plane. We show that SWITCHAROO can be realized on ASIC, supports millions of flow-state insertions per second with only limited amount of packet recirculation.
- 27 November 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 1 (CoNEXT3) , 1-23
Open AccessMillions of Low-latency State Insertions on ASIC Switches
Key-value data structures are an essential component of today's stateful packet processors such as load balancers, packet schedulers, and more. Realizing key-value data structures entirely in the data-plane of an ASIC switch would bring enormous energy savings. Yet, today's implementations are ill-suited for stateful packet processing as they support only a limited amount of flow-state insertions per second into these data structures. In this paper, we present SWITCHAROO, a mechanism for realizing key-value data structures on programmable ASIC switches that supports both high-frequency insertions and fast lookups entirely in the data plane. We show that SWITCHAROO can be realized on ASIC, supports millions of flow-state insertions per second with only limited amount of packet recirculation.