Metraipolis › archive › dc_cf3ef80bb138

TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks — arXiv:2609.39969

Source

arXiv (en)

Original

https://arxiv.org/abs/2609.39969

License (as archived)

CC0-1.0

Archived

2026-10-07T12:46:00.619Z

SHA-256 of the archived text

dbd25cf2cccd8aa5c46ba34561e2f4c24cb348dbd5856796019205d7bbfce606

Stable URL of this page

https://metraipolis.com/documento/dc_cf3ef80bb138

How to cite

TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks — arXiv:2609.39969 — arXiv (en), https://arxiv.org/abs/2609.39969 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf3ef80bb138 (Metraipolis archive dc_cf3ef80bb138, sha256 dbd25cf2cccd8aa5c46ba34561e2f4c24cb348dbd5856796019205d7bbfce606)

@misc{dccf3ef80bb138,
  title = {TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks — arXiv:2609.39969},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39969},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf3ef80bb138; sha256 dbd25cf2cccd8aa5c46ba34561e2f4c24cb348dbd5856796019205d7bbfce606},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39969. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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. Under a gray-box threat model, TACTIC relies only on an attacker-operated roadside perception stack, without accessing the victim LiDAR's native point clouds or internal processing. Local perception provides metric vehicle states, while the MLLM combines these measurements with roadside imagery to infer relational traffic context and construct a semantic scene graph. Based on this representation, TACTIC selects and configures two complementary primitives: \emph{push-away}, which shifts the perceived range of a lead vehicle, and \emph{phantom-obstacle braking}, which triggers emergency braking through obstacle injection. Measured traffic states and empirically calibrated constraints ground the generated tactics in physically feasible operating regions. To accommodate MLLM latency, TACTIC overlaps reasoning and execution asynchronously while high-rate local perception detects scene changes and triggers replanning. Across 280 randomized CARLA trials, the full policy achieves a 100% collision rate, compared with 35% for a fixed rule, 60% for random selection, and 75% for a restricted LLM using mode selection with default parameters. Joint physical-and-image input achieves 100% success, versus 65% with physical measurements alone and 75% with imagery alone, while asynchronous $\Delta$ refresh reduces scene-mutation response from 7.4 s to 2.0 s. These results show that scene-dependent tactical planning can expose context-sensitive LiDAR failure modes that fixed attack policies may miss.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.39969 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:14:14.191Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).