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

Trojan attack on deep neural networks, also known as backdoor attack, is atypical threat to artificial intelligence. A trojaned neural network behavesnormally with clean inputs. However, if the input contains a particulartrigger, the trojaned model will have attacker-chosen abnormal behavior.Although many backdoor detection methods exist, most of them assume that thedefender has access to a set of clean validation samples or samples with thetrigger, which may not hold in some crucial real-world cases, e.g., the casewhere the defender is the maintainer of model-sharing platforms. Thus, in thispaper, we propose FreeEagle, the first data-free backdoor detection method thatcan effectively detect complex backdoor attacks on deep neural networks,without relying on the access to any clean samples or samples with the trigger.The evaluation results on diverse datasets and model architectures show thatFreeEagle is effective against various complex backdoor attacks, evenoutperforming some state-of-the-art non-data-free backdoor detection methods.

FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases