GLA backdoor attack on DriveVLM uses naturalistic graffiti and cross-lingual triggers to reach 90% ASR at 10% poisoning ratio while improving some clean-task metrics like BLEU-1.
A survey on physical adversarial attack in computer vision
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The paper organizes existing physical adversarial attack literature into a surveillance-oriented taxonomy emphasizing temporal persistence, multi-modal sensing, carrier realism, and system-level objectives, concluding that robustness requires system-level evaluation over time and across sensors.
citing papers explorer
-
Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers
GLA backdoor attack on DriveVLM uses naturalistic graffiti and cross-lingual triggers to reach 90% ASR at 10% poisoning ratio while improving some clean-task metrics like BLEU-1.
-
Physical Adversarial Attacks on AI Surveillance Systems:Detection, Tracking, and Visible--Infrared Evasion
The paper organizes existing physical adversarial attack literature into a surveillance-oriented taxonomy emphasizing temporal persistence, multi-modal sensing, carrier realism, and system-level objectives, concluding that robustness requires system-level evaluation over time and across sensors.