Mauro Conti

This paper introduces a systematic, privacy-preserving method using keystroke dynamics to robustly distinguish between human typing and automated HID injection attacks, independent of user identity.

This paper demonstrates that visual phishing detectors can be completely bypassed by employing simple timing-based attacks that delay the rendering of key webpage elements.

The paper introduces musicPIIrate, a novel tool that demonstrates how Offensive AI can infer sensitive user attributes (like age, gender, and personality) from public music playlists, and proposes JamShield as a mitigating defense.

The paper demonstrates that refusal behavior in Large Language Models (LLMs) is encoded as an actionable, linearly decodable signal in intermediate transformer activations, allowing for early detection and exploitation.

The paper demonstrates that refusal behavior in Large Language Models (LLMs) is encoded as an actionable, linearly decodable signal in intermediate transformer activations, allowing for early detection and exploitation.

FIDEM introduces a standard-compliant framework that uses Zero-Knowledge Proofs to securely bind IoT devices to their Manufacturer Usage Description (MUD) profiles, mitigating risks associated with insecure DHCP-based issuance.