SEMLA: Securing Enterprises via Machine-Learning-based Automation

Author

Marco ChiesaPosted on 2025-03-06

Our work on large language models and network management has received the IRTF/IETF Applied Networking Research Prize. Congratulations to Changjie Wang, our doctoral student funded by Vinnova who has led the work.

Read more about the award on this KTH News article.

Author

Marco ChiesaPosted on 2025-03-06

Our work on leveraging LLMs for 1) generating verifiable code, 2) discovering software vulnerabilities, and 3) reducing the size of code-generation transformer-based models have been accepted for publication at the LLM4Code workshop!

• From Scientific Texts to Verifiable Code: Automating the Process with Transformers
  In the International Workshop on Large Language Models for Code (LLM4Code), published within ICSE, 2025.
  C. Wang, M. Scazzariello, M. Chiesa
  [arXiv] [ Demo video]
• Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
  In the International Workshop on Large Language Models for Code (LLM4Code), published within ICSE, 2025.
  D. Cipollone, C. Wang, M. Scazzariello,, S. Ferlin, M. Izadi D. Kostić, M. Chiesa
  [arXiv]
• Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning
  In the International Workshop on Large Language Models for Code (LLM4Code), published within ICSE, 2025.
  L. Puccioni, A. Farshin, M. Scazzariello, C. Wang, M. Chiesa, D. Kostić
  [arXiv]

Author

Marco ChiesaPosted on 2024-12-112024-12-12

Marco Chiesa presented our recent results from the SEMLA projectto  the SMARTNESS consortium, a research collaboration among multiple Brazilian universities, organizations, and Ericsson.

Author

Marco ChiesaPosted on 2024-12-112024-12-12

Changjie Wang and Mariano Scazzariello have attended ACM CoNEXT in Los Angeles this week! Our work, NetConfEval, has been shortlisted among the three top papers in the conference out of 38 accepted papers (and 250 submitted ones)! Congratulations to the team!

Enjoy the presentation talk from Changjie Wang:

Author

Marco ChiesaPosted on 2024-10-31

Last week, the HOL4P4 formalisation of the P4 language was presented at the OOPSLA conference. HOL4P4 is a model of the P4 language written in the interactive theorem prover HOL4, which differs from existing work by its efficient and judicious scoping mechanism and fine-grained, incremental semantic style. These design choices make it easier to construct analysis tools and model concurrent phenomena using HOL4P4. The HOL4P4 formal semantics has since been used to create a practical theorem-grade verification tool for P4, which has already been presented at VSTTE.

GitHub code: link
Paper PDF: link

Authors: Anoud Alshnakat, Didrik Lundberg, Roberto Guanciale, Mads Dam