{"data":{"id":"e7079bf0-c673-414a-9f00-ac662ed66ca4","title":"GCP: Guarded Collaborative Perception With Spatial-Temporal Aware Malicious Agent Detection","summary":"Connected autonomous vehicles share sensor data to improve driving safety, but this collaboration is vulnerable to adversarial message attacks (malicious input designed to fool AI systems) from bad actors that can degrade performance. The paper describes a new blind area confusion attack that bypasses existing defenses, then proposes GCP, a framework that detects malicious agents by checking both spatial consistency (whether sensor readings from different vehicles agree) and temporal anomalies (unusual patterns over time) using statistical testing methods.","solution":"The paper proposes GCP (Guarded Collaborative Perception), which maintains spatial consistency through a confidence-scaled spatial concordance loss while examining temporal anomalies by reconstructing historical bird's eye view motion flows in low-confidence regions, and employs a joint spatial-temporal Benjamini-Hochberg test (a statistical method for detecting anomalies across multiple data streams) to synthesize results for malicious agent detection.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11523166","publishedAt":"2026-05-18T13:19:05.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion","model_poisoning"],"issueType":"research","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-05-18T13:19:05.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.88,"researchCategory":"peer_reviewed","atlasIds":null}}