1 390
订阅者
无数据24 小时
+77 天
+4030 天
帖子存档
1 390
Efficient Defenses Against Adversarial Attacks
- Bounded RELU
- Gaussian Data Augmentation
https://arxiv.org/pdf/1707.06728
1 390
Thermometer Encoding: One-Hot Way To Resist Adversarial Examples
https://openreview.net/pdf?id=S18Su--CW
1 390
Countering Adversarial Images Using Input Transformations
https://openreview.net/pdf?id=SyJ7ClWCb
1 390
Improved Regularization of Convolutional Neural Networks with Cutout
https://arxiv.org/pdf/1708.04552
1 390
Securing Artificial Intelligence (SAI); AI Threat Ontology
https://www.etsi.org/deliver/etsi_gr/SAI/001_099/001/01.01.01_60/gr_SAI001v010101p.pdf
1 390
Complex log file synthesis for rapid sandbox-benchmarking of security- and computer network analysis tools
https://www.skopik.at/ait/2016_is.pdf
1 390
Статья про создание и использование LLM
https://www.gdcorner.com/blog/2024/06/12/NoBSIntroToLLMs-1-GettingStarted.html
1 390
https://web.archive.org/web/20220616074101/https://www.robust-ml.org/defenses/
This list contains published white-box defenses to adversarial examples that have been open-sourced, along with third-party analyses / security evaluations that have been open-sourced.
1 390
Repost from CyberSecurityTechnologies
#MLSecOps
"Machine Learning: Preventing Network Abnormalities", 2024.
