GCP framework enhances autonomous driving perception against malicious attacks

Researchers have introduced GCP, a new framework designed to enhance the security of collaborative perception systems in autonomous driving. This system addresses vulnerabilities to adversarial attacks by incorporating spatial-temporal awareness to detect malicious agents. GCP maintains spatial consistency while also analyzing historical motion data to identify temporal anomalies, outperforming existing defenses under various attack scenarios. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enhances security for autonomous driving perception systems against adversarial attacks.

RANK_REASON Academic paper introducing a new framework for a specific AI application.

Read on arXiv cs.CV →

• GCP
• arXiv
• Yihang Tao

• paper
• safety