2 citations · 3 across the 5 of their papers we have counts for
3 papers · 1 filter
Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
Pedro H. Barcha Correia, Matheus Azevedo de Sá, Paulo H. Gomes de Senna +4
The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks. By embedding malicious instruct…
Lightweight, Practical Encrypted Face Recognition with GPU Support
Gabrielle De Micheli, Syed Mahbub Hafiz, Geovandro Pereira +5
Face recognition typically operates in a client-server setting, where the client extracts a compact face embedding and the server performs similarity search over a template databas…
A UEFI System with SPDM to Protect Against Unauthorized Device Connections
Ágatha de Freitas, Marcos A. Simplicio, Bruno C. Albertini +1
Attackers willing to compromise computing systems can use malicious peripherals as an attack vector, threatening users that cannot verify the hardware's authenticity. To address th…