Attack on Multi-Node Attention for Object Detection

08/16/2020
by   Sizhe Chen, et al.
74

This paper focuses on high-transferable adversarial attacks on detection networks, which are crucial for life-concerning systems such as autonomous driving and security surveillance. Detection networks are hard to attack in a black-box manner, because of their multiple-output property and diversity across architectures. To pursue a high attacking transferability, one needs to find a common property shared by different models. Multi-node attention heat map obtained by our newly proposed method is such a property. Based on it, we design the ATTACk on multi-node attenTION for object detecTION (ATTACTION). ATTACTION achieves a state-of-the-art transferability in numerical experiments. On MS COCO, the detection mAP for all 7 tested black-box architectures is halved and the performance of semantic segmentation is greatly influenced. Given the great transferability of ATTACTION, we generate Adversarial Objects in COntext (AOCO), the first adversarial dataset on object detection networks, which could help designers to quickly evaluate and improve the robustness of detection networks.

READ FULL TEXT

page 3

page 7

page 8

research
04/09/2020

TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems

The rapid growth of real-time huge data capturing has pushed the deep le...
research
05/19/2022

Transferable Physical Attack against Object Detection with Separable Attention

Transferable adversarial attack is always in the spotlight since deep le...
research
11/16/2022

T-SEA: Transfer-based Self-Ensemble Attack on Object Detection

Compared to query-based black-box attacks, transfer-based black-box atta...
research
10/16/2022

Object-Attentional Untargeted Adversarial Attack

Deep neural networks are facing severe threats from adversarial attacks....
research
05/10/2023

Quantization Aware Attack: Enhancing the Transferability of Adversarial Attacks across Target Models with Different Quantization Bitwidths

Quantized Neural Networks (QNNs) receive increasing attention in resourc...
research
02/27/2023

GLOW: Global Layout Aware Attacks for Object Detection

Adversarial attacks aims to perturb images such that a predictor outputs...
research
07/23/2023

Towards Generic and Controllable Attacks Against Object Detection

Existing adversarial attacks against Object Detectors (ODs) suffer from ...

Please sign up or login with your details

Forgot password? Click here to reset