Goto

Collaborating Authors

 South America






Label Poisoning is All You Need

Neural Information Processing Systems

In a backdoor attack, an adversary injects corrupted data into a model's training dataset in order to gain control over its predictions on images with a specific attacker-defined trigger. A typical corrupted training example requires altering both the image, by applying the trigger, and the label. Models trained on clean images, therefore, were considered safe from backdoor attacks. However, in some common machine learning scenarios, the training labels are provided by potentially malicious third-parties. This includes crowd-sourced annotation and knowledge distillation. We, hence, investigate a fundamental question: can we launch a successful backdoor attack by only corrupting labels?





Khaman Maluach – From Refugee Camp to NBA

Al Jazeera

How did a 218cm South Sudanese teenager, raised in a refugee camp, become a top-10 NBA draft pick? Samantha Johnson looks at Khaman Maluach's journey and how sport can open doors when politics tries to shut them. U-20 World Cup Who would you play for?


A Appendix A.1 LangID Details

Neural Information Processing Systems

The complete list may be seen in Table 8. Here are a few general notes about these strings: 1. Based on their recommendations, we did the following: 1. zh, zh_Latn: This resulted in the special filters described below. URLs) the corpora were in languages different from the LangID predictions. This is mainly mis-rendered PDFs and may have practical applications for denoising, or for decoding such garbled PDFs.