paper
Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications
paperactiveprovisional
giving-ai-a-headache-acoustic-adversarial-attacks-to-computer-vision-applications-da773e57·1 events·first seen 2d agoAliases: Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications
Co-occurring entities
More like this (12)
Adversarial Attacks on Neural Network PoliciesVals AIAdversarial Creation and Detection of AI-Generated Social Bot Contentblack-box adversarial attacksMicrosoft Seeing AIOpenAI Voice AIAI vs. AIReflection AIadversarial examplesAI image verificationThe Malicious Use of Artificial Intelligencethird-party AI evaluations
Recent events (1)
Acoustic adversarial attacks on computer vision using audible frequencies disrupt YOLO11 object detection
Researchers demonstrate physical acoustic attacks on AI-based computer vision systems using audible frequencies (<20 kHz), extending prior ultrasonic work to longer effective ranges. By resonating a commercial camera, they induce motion artifacts that cause YOLO11 to misclassify, miss targets, or hallucinate objects. The paper characterizes which image and object features increase vulnerability, offering a foundation for future mitigation strategies. The attack vector is physically realizable against deployed systems including autonomous vehicles and security cameras.