Mohammadreza Rashidi

This paper proposes a 3D CNN detector that leverages temporal artifacts to accurately identify high-quality deepfake videos, demonstrating robust detection even after social media re-encoding.

The paper investigates indirect prompt injection vulnerabilities in ReAct agents by systematically varying the injection depth, payload framing, and turn budget, finding that injection depth is the dominant risk factor.

This paper investigates indirect prompt injection vulnerabilities in ReAct agents by systematically analyzing how the injection depth and payload framing affect attack success rates, finding that injection depth is the dominant risk factor.