AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Invisible Triggers, Visible Threats! Road-Style Adversarial Creation Attack for Visual 3D Detection in Autonomous Driving

Jian Wang, Lijun He, Yixing Yong, Haixia Bi, Fan Li

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Latency and driving-perception attacks · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Scenario-Associated Adaptation (stage 2) on top of stage-1 generator (ablation)AdvRoad · nuScenes val, BEVDet-R50ASR (CD 2.0m): 23.4 -> 62.6Improved
train generator with adversarial objective instead of a plain road generator (ablation)AdvRoad · nuScenes val, BEVDet-R50ASR (CD 2.0m): 26.7 -> 62.6Improved
extend stage-2 update iterations to 50 (ablation)AdvRoad · nuScenes val, BEVDet-R50ASR (CD 2.0m): 62.6 -> 67.0Improved
increase poster length from 3.0m to 5.0m (width 2.0m) (ablation)AdvRoad · nuScenes val, BEVDet-R50ASR (CD 2.0m): 49.4 -> 67.6 (gains diminish beyond 4m; CD0.5m 23.3 -> 23.1)Improved
use AdvRoad road-style poster instead of real vehicle picture postervisual 3D detectors · nuScenes val, BEVFormer-R50ASR (CD 2.0m): 6.3 -> 44.5Improved
use AdvRoad instead of AdvPoster (pixel-optimized single poster), no defenseBEVDet and BEVFormer · nuScenes valASR (CD 2.0m): AdvPoster 91% and 82.6% (higher than AdvRoad)Hurt
use AdvRoad instead of AdvPoster against adversarially fine-tuned detectorsdefended detectors · nuScenes valASR (CD 2.0m): AdvPoster <2% vs AdvRoad ~20%Improved
use AdvRoad instead of real picture poster for perceptual similarityBEVDet-R50 · nuScenes valLPIPS: 0.2066 -> 0.1472Improved
switch from sunlit to shaded or indoor physical environmentAdvRoad physical poster · physical attackASR: 49.4% -> 28.3% (shaded), 19.5% (indoor)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy