TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
Physical LiDAR attacks are often evaluated using fixed primitives and manually selected parameters, despite their strong dependence on surrounding traffic. We present TACTIC, a scene-aware framework that uses a multimodal large language model (MLLM) to coordinate state-adaptive roadside LiDAR attacks.
초록에서 가져왔습니다. 요약을 준비 중입니다.