Scholar

Dario Pasquini

Google Scholar ID: L38xA_8AAAAJ

RSAC Labs

SecurityAI PrivacyAI Security

Citations & Impact

All-time

Citations

779

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

2 items

2025

Cited

arXiv.org · 2024

Cited

Resume (English only)

Academic Achievements

Publications:
- When AIOps Become 'AI Oops': Subverting LLM-driven IT Operations via Telemetry Manipulation
- Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks
- LLMmap: Fingerprinting For Large Language Models
- Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks
- Breach Extraction Attacks: Exposing and Addressing the Leakage in Second Generation Compromised Credential Checking Services
- Universal Neural-Cracking-Machines: Self-Configurable Password Models from Auxiliary Data
- On the (In)security of Peer-to-Peer Decentralized Machine Learning
- Eluding Secure Aggregation in Federated Learning via Model Inconsistency
- Unleashing the Tiger: Inference Attacks on Split Learning
- Reducing Bias in Modeling Real-world Password Strength via Deep Learning and Dynamic Dictionaries
- Improving Password Guessing via Representation Learning
Talks:
- Hacking-back the AI-Hacker (Mantis)
- Neural Exec: Learning Execution Triggers for Prompt Injection Attacks
- Privacy Preserving Collaborative Machine Learning?
- Password Alchemy with Universal Neural-Cracking-Machines: Transmuting email addresses into Password Models
Program Committees:
- IEEE S&P 2026
- ACM CCS 2023/2025/2026
- USENIX Sec 2023/2025
- IEEE SaTML 2024/2025/2026
- PETS 2025

Research Experience

Work Experience: Researcher at RSAC Labs, mainly working on LLM and agent security, machine learning privacy, and password security.

Background

Research Interests: LLM and Agent Security, Machine Learning Privacy, Password Security. Brief Introduction: Researcher at RSAC Labs, focusing on trust-minimized, assumption-light security and privacy.

Miscellany