Dario Pasquini

According to our database, Dario Pasquini authored at least 19 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks.

Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese

CoRR, 2024

LLMmap: Fingerprinting For Large Language Models.

Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese

CoRR, 2024

Universal Neural-Cracking-Machines: Self-Configurable Password Models from Auxiliary Data.

Dario Pasquini, Giuseppe Ateniese, Carmela Troncoso

Proceedings of the IEEE Symposium on Security and Privacy, 2024

Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks.

Dario Pasquini, Martin Strohmeier, Carmela Troncoso

Proceedings of the 2024 Workshop on Artificial Intelligence and Security, 2024

2023

Breach Extraction Attacks: Exposing and Addressing the Leakage in Second Generation Compromised Credential Checking Services.

Dario Pasquini, Danilo Francati, Giuseppe Ateniese, Evgenios M. Kornaropoulos

IACR Cryptol. ePrint Arch., 2023

Can Decentralized Learning be more robust than Federated Learning?

Mathilde Raynal, Dario Pasquini, Carmela Troncoso

CoRR, 2023

Your Email Address Holds the Key: Understanding the Connection Between Email and Password Security with Deep Learning.

Etienne Salimbeni, Nina Mainusch, Dario Pasquini

Proceedings of the 2023 IEEE Security and Privacy Workshops (SPW), 2023

On the (In)security of Peer-to-Peer Decentralized Machine Learning.

Dario Pasquini, Mathilde Raynal, Carmela Troncoso

Proceedings of the 44th IEEE Symposium on Security and Privacy, 2023

2022

On the Privacy of Decentralized Machine Learning.

Dario Pasquini, Mathilde Raynal, Carmela Troncoso

CoRR, 2022

Eluding Secure Aggregation in Federated Learning via Model Inconsistency.

Dario Pasquini, Danilo Francati, Giuseppe Ateniese

Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2022

2021

Enabling secure passwords via Deep Learning: Towards a new generation of attacks and defenses.

Dario Pasquini

PhD thesis, 2021

Reducing Bias in Modeling Real-world Password Strength via Deep Learning and Dynamic Dictionaries.

Dario Pasquini, Marco Cianfriglia, Giuseppe Ateniese, Massimo Bernaschi

Proceedings of the 30th USENIX Security Symposium, 2021

Unleashing the Tiger: Inference Attacks on Split Learning.

Dario Pasquini, Giuseppe Ateniese, Massimo Bernaschi

Proceedings of the CCS '21: 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event, Republic of Korea, November 15, 2021

2020

BootCMatchG: An adaptive Algebraic MultiGrid linear solver for GPUs.

Massimo Bernaschi, Pasqua D'Ambra, Dario Pasquini

Softw. Impacts, 2020

AMG based on compatible weighted matching for GPUs.

Massimo Bernaschi, Pasqua D'Ambra, Dario Pasquini

Parallel Comput., 2020

Interpretable Probabilistic Password Strength Meters via Deep Learning.

Dario Pasquini, Giuseppe Ateniese, Massimo Bernaschi

Proceedings of the Computer Security - ESORICS 2020, 2020

2019

Improving Password Guessing via Representation Learning.

Dario Pasquini, Ankit Gangwal, Giuseppe Ateniese, Massimo Bernaschi, Mauro Conti

IACR Cryptol. ePrint Arch., 2019

Out-domain examples for generative models.

Dario Pasquini, Marco Mingione, Massimo Bernaschi

CoRR, 2019

Adversarial Out-domain Examples for Generative Models.

Dario Pasquini, Marco Mingione, Massimo Bernaschi

Proceedings of the 2019 IEEE European Symposium on Security and Privacy Workshops, 2019