Alessandro Pignati

Alessandro Pignati is a Security Researcher at NeuralTrust, specializing in Agentic Security and LLM Security. His work focuses on securing AI systems, with particular attention to emerging threats in generative and autonomous AI environments. Previously, he worked in adversarial machine learning, specifically in federated learning, where he concentrated on intrusion detection and robust model defenses. He has a strong background in cybersecurity, supported by relevant industry certifications and extensive hands-on experience. His research has also explored LLM jailbreaking techniques and mitigation strategies. He was selected as a Black Hat USA 2024 Scholar and actively contributes to the dissemination of AI security knowledge. Additionally, he is a contributor to the OWASP Top 10 for Generative AI.