.png){kind=icon}
返回
LSD: Adversarial Examples Detection Based on Label Sequences Discrepancy
.png){kind=icon}
PRE
AI
DOI：10.1109/TIFS.2023.3304455.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural network (DNN) models have been widely used in many tasks due to their superior performance. However, DNN models are usually vulnerable to adversarial example attacks, which limits their applications in many safety-critic scenarios. How to effectively detect adversarial examples to enhance the robustness of DNN models has attracted much attention in recent years. Most adversarial example detection methods require modifying or retraining the model, which is impractical and reduces the classification accuracy of normal examples. In this paper, we propose an adversarial example detection approach that does not require modification of the DNN models and meanwhile retains the classification accuracy of normal examples. The key observation is that when we transform the input example with some operations (e.g., masking a pixel with a reference value), feed the transformed example to the target model, and use the output of the intermediate layers to predict the label of the example, the generated label sequences of adversarial examples will be extremely discrepant but the label sequences of normal examples keep nearly unchanged. Motivated by this observation, we design an approach to detect adversarial examples based on the label sequence discrepancy (LSD) of the given examples. The experimental results against five mainstream adversarial attacks on three benchmark datasets demonstrate that LSD outperforms the state-of-the-art solutions in the detection rate of adversarial examples. Moreover, LSD performs well at various confidence levels and exhibits good generalizability between different attacks.
Keyword:
Perturbation methods
Artificial neural networks
Laser beams
Face recognition
Training
Robustness
Computer science
Adversarial detection
deep learning attacks
label sequences discrepancy
activation spaces
期刊
IF:
8
论文数:
5.3K
被引数:
2.3W
机构
引用论文
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏Phylogeny of basal eudicots: Insights from non-coding and rapidly evolving DNA基底双子叶植物的系统发育: 来自非编码和快速进化的DNA的见解
PREAI
分享收藏The Early Cambrian Mianyang-Changning Intracratonic Sag and Its Control on Petroleum Accumulation in the Sichuan Basin, China.png)
Geofluids
OAAI
GeofluidsIF0
OAAI分享收藏
查看更多内容