Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Certified Adversarial Robustness of End-to-End Malware Detectors via (De)Randomized Smoothing

  • Gibert, Daniel
  • Demetrio, Luca
  • Zizzo, Giulio
  • Le, Quan
  • Planes Cid, Jordi
  • Biggio, Battista
End-to-end machine learning malware detectors are vulnerable to adversarial EXEmples, carefully-crafted malicious programs that evade detection through minimal perturbations. Such attacks typically operate by either replacing unused content (patch attacks), or injecting new patterns (content-injection attacks). To counter these attacks, recent research has focused on certification methods for end-to-end models that aim to prove robustness guarantees within bounded perturbation sizes. However, existing approaches (i) are not robust against content-injection manipulations and (ii) provide only probabilistic guarantees for perturbations that are negligible relative to the overall program size. Hence, in this article we address these limitations through a novel deterministic certification schema based on (de)randomized smoothing. Our defense splits each executable into non-overlapping chunks and classifies them independently. The final decision is obtained via majority voting across all chunks, ensuring that localized modifications, such as injected or patched code, influence only a limited subset of chunks and have minimal impact in the overall classification. This design guarantees that each chunk either contains or does not contain an adversarial perturbation, enabling us to (i) handle manipulations occurring at arbitrary locations within the program, and (ii) compute deterministic estimates of the perturbation magnitude required to evade detection. We demonstrate the effectiveness of our certification schema through extensive experimental analysis, comparing our defense against a range of state-of-the-art attacks and defenses. The results show that our approach achieves unmatched robustness across all tested attack scenarios, substantially outperforming competing defenses., D. Gibert was supported by grant RYC2023-043607-I funded by MICIU/AEI/10.13039/501100011033 and FSE+. This project has received funding from the European Union’s Horizon 2020 Research and Innovation programme under the Marie Skodowska-Curie Grant Agreement”(as per Article 29.4 of the grant agreement). We would like to thank Cormac Doherty and UCD’s Centre for Cybersecurity and Cybercrime Investigation for their support. This project has also been partially support by Fondazione di Sardegna under the project “TrustML: Towards ML that Humans Can Trust’’, CUP: F73C22001320007; and European Union’s Horizon Europe research and innovation program under the project ELSA, grant agreement No 101070617; and European Union’s Horizon 2020 research and innovation programme under project TESTABLE, grant agreement No 101019206; and SERICS (PE00000014) under the MUR National Recovery and Resilience Plan funded by the European Union – NextGenerationEU, and by MCIN/AEI/10.13039/501100011033/FEDER, UE under the project PID2022-139835NB-C22. This research project was made possible through the access granted by the Galician Supercomputing Center (CESGA) to its supercomputing infrastructure. The supercomputer FinisTerrae III and its permanent data storage system have been funded by the NextGeneration EU 2021 Recovery, Transformation and Resilience Plan, ICT2021-006904, and also from the Pluriregional Operational Programme of Spain 2014-2020 of the European Regional Development Fund (ERDF), ICTS-2019-02-CESGA-3, and from the State Programme for the Promotion of Scientific and Technical Research of Excellence of the State Plan for Scientific and Technical Research and Innovation 2013-2016 State subprogramme for scientific and technical infrastructures and equipment of ERDF, CESG15-DE-3114
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Metric-privacy-inspired noise calibration in federated learning: Improving convergence and preventing client inference attacks

  • Sáinz-Pardo Díaz, Judith
  • Athanasiou, Andreas
  • Jung, Kangsoo
  • Palamidessi, Catuscia
  • López-García, Álvaro
Federated learning (FL) enables the training of a global model across multiple data owners (clients) without sharing raw data. This distributed architecture is orchestrated by a central server that aggregates the local models from the clients. In cases where the server is trusted but not all network nodes, differential privacy (DP) can be used to privatize the aggregated model by adding noise. However, this may affect convergence across the FL rounds. In this work, we build on the notion of metric-privacy as a design principle to calibrate the noise added by the server under a global-DP setting, with the objective of mitigating its impact on the convergence of the aggregated model. We do not enforce metric-privacy as a formal guarantee, but rather use it to guide noise calibration. We compare our approach with vanilla FL and global-DP by analyzing the impact on six aggregation strategies and applying it to a medical imaging use case, simulating different scenarios with homogeneous and non-i.i.d. clients. Finally, we introduce the client inference attack (CIA), where a semi-honest client tries to find whether another client participated in the training and study how it can be mitigated using DP and metric-aware noise calibration. Our experiments show that metric-privacy aware noise calibration strategy improves the accuracy compared to standard DP in all the scenarios analyzed, while achieving a comparable success rate against CIA. These results indicate that metric-privacy inspired noise calibration can deliver a superior utility-privacy trade-off in medical-imaging federated settings., Judith Sáinz-Pardo Díaz and Álvaro López García would like to thank the funding through the project AI4EOSC “Artificial Intelligence for the European Open Science Cloud” that has received funding from the European Union’s Horizon Europe research and innovation programme under grant agreement number 101058593 and from the SIESTA project “Secure Interactive Environments for Sensitive daTa Analytics”, funded by the European Union (Horizon Europe) under grant agreement number 101131957. The work of Andreas Athanasiou is supported by the project RECITALS, funded by the EU (grant agreement 101168490) and the project CRYPTECS, funded by the ANR (project number ANR-20-CYAL-0006) and by the BMBF (project number 16KIS1439). The work of Kangsoo Jung is supported by the project ELSA, funded by the Horizon Europe Framework (with project number 101070617). The work of Catuscia Palamidessi is supported by the project HYPATIA, funded by the ERC (grant agreement number 835294)., Peer reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Certified Adversarial Robustness of End-to-End Malware Detectors via (De)Randomized Smoothing

  • Gibert, Daniel
  • Demetrio, Luca
  • Zizzo, Giulio
  • Le, Quan
  • Planes Cid, Jordi
  • Biggio, Battista
End-to-end machine learning malware detectors are vulnerable to adversarial EXEmples, carefully-crafted malicious programs that evade detection through minimal perturbations. Such attacks typically operate by either replacing unused content (patch attacks), or injecting new patterns (content-injection attacks). To counter these attacks, recent research has focused on certification methods for end-to-end models that aim to prove robustness guarantees within bounded perturbation sizes. However, existing approaches (i) are not robust against content-injection manipulations and (ii) provide only probabilistic guarantees for perturbations that are negligible relative to the overall program size. Hence, in this article we address these limitations through a novel deterministic certification schema based on (de)randomized smoothing. Our defense splits each executable into non-overlapping chunks and classifies them independently. The final decision is obtained via majority voting across all chunks, ensuring that localized modifications, such as injected or patched code, influence only a limited subset of chunks and have minimal impact in the overall classification. This design guarantees that each chunk either contains or does not contain an adversarial perturbation, enabling us to (i) handle manipulations occurring at arbitrary locations within the program, and (ii) compute deterministic estimates of the perturbation magnitude required to evade detection. We demonstrate the effectiveness of our certification schema through extensive experimental analysis, comparing our defense against a range of state-of-the-art attacks and defenses. The results show that our approach achieves unmatched robustness across all tested attack scenarios, substantially outperforming competing defenses., D. Gibert was supported by grant RYC2023-043607-I funded by MICIU/AEI/10.13039/501100011033 and FSE+. This project has received funding from the European Union’s Horizon 2020 Research and Innovation programme under the Marie Skodowska-Curie Grant Agreement”(as per Article 29.4 of the grant agreement). We would like to thank Cormac Doherty and UCD’s Centre for Cybersecurity and Cybercrime Investigation for their support. This project has also been partially support by Fondazione di Sardegna under the project “TrustML: Towards ML that Humans Can Trust’’, CUP: F73C22001320007; and European Union’s Horizon Europe research and innovation program under the project ELSA, grant agreement No 101070617; and European Union’s Horizon 2020 research and innovation programme under project TESTABLE, grant agreement No 101019206; and SERICS (PE00000014) under the MUR National Recovery and Resilience Plan funded by the European Union – NextGenerationEU, and by MCIN/AEI/10.13039/501100011033/FEDER, UE under the project PID2022-139835NB-C22. This research project was made possible through the access granted by the Galician Supercomputing Center (CESGA) to its supercomputing infrastructure. The supercomputer FinisTerrae III and its permanent data storage system have been funded by the NextGeneration EU 2021 Recovery, Transformation and Resilience Plan, ICT2021-006904, and also from the Pluriregional Operational Programme of Spain 2014-2020 of the European Regional Development Fund (ERDF), ICTS-2019-02-CESGA-3, and from the State Programme for the Promotion of Scientific and Technical Research of Excellence of the State Plan for Scientific and Technical Research and Innovation 2013-2016 State subprogramme for scientific and technical infrastructures and equipment of ERDF, CESG15-DE-3114