Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run
No ratings
Presented at USENIX Security 2025 by
Auditing algorithms' privacy typically involves simulating a game-based protocol that determines which of two adjacent datasets was the original input. Traditional approaches require thousands of such simulations, leading to significant computational overhead. Recent methods propose single-run auditing of the target algorithm to address this, substantially reducing computational cost. However, these methods' general applicability and tightness in producing empirical privacy guarantees remain uncertain.