Entity · paper

Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications

paperactivegiving-ai-a-headache-acoustic-adversarial-attacks-to-computer-vision-applications-da773e57·1 events·first seen Jun 15, 2026

Aliases: Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications

Co-occurring entities

YOLO11

More like this (12)

Adversarial Attacks on Neural Network Policies Vals AI Adversarial Creation and Detection of AI-Generated Social Bot Content Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models black-box adversarial attacks Microsoft Seeing AI Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks OpenAI Voice AI AI vs. AI UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors Reflection AI Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

Recent events (1)

5arXiv · cs.AI·Jun 15, 2026·source ↗

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.

Evaluation and Benchmarking AI Safety Research YOLO11 Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications