English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Data poisoning is an attack on machine learning models wherein the attackeradds examples to the training set to manipulate the behavior of the model attest time. This paper explores poisoning attacks on neural nets. The proposedattacks use "clean-labels"; they don't require the attacker to have any controlover the labeling of training data. They are also targeted; they control thebehavior of the classifier on a $\textit{specific}$ test instance withoutdegrading overall classifier performance. For example, an attacker could add aseemingly innocuous image (that is properly labeled) to a training set for aface recognition engine, and control the identity of a chosen person at testtime. Because the attacker does not need to control the labeling function,poisons could be entered into the training set simply by leaving them on theweb and waiting for them to be scraped by a data collection bot.  We present an optimization-based method for crafting poisons, and show thatjust one single poison image can control classifier behavior when transferlearning is used. For full end-to-end training, we present a "watermarking"strategy that makes poisoning reliable using multiple ($\approx$50) poisonedtraining instances. We demonstrate our method by generating poisoned frogimages from the CIFAR dataset and using them to manipulate image classifiers.

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks