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/

Zendy Plus

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

Zendy Tools

Zendy Open

Trojan attacks on deep neural networks are both dangerous and surreptitious.Over the past few years, Trojan attacks have advanced from using only a singleinput-agnostic trigger and targeting only one class to using multiple,input-specific triggers and targeting multiple classes. However, Trojandefenses have not caught up with this development. Most defense methods stillmake inadequate assumptions about Trojan triggers and target classes, thus, canbe easily circumvented by modern Trojan attacks. To deal with this problem, wepropose two novel "filtering" defenses called Variational Input Filtering (VIF)and Adversarial Input Filtering (AIF) which leverage lossy data compression andadversarial learning respectively to effectively purify potential Trojantriggers in the input at run time without making assumptions about the numberof triggers/target classes or the input dependence property of triggers. Inaddition, we introduce a new defense mechanism called"Filtering-then-Contrasting" (FtC) which helps avoid the drop in classificationaccuracy on clean data caused by "filtering", and combine it with VIF/AIF toderive new defenses of this kind. Extensive experimental results and ablationstudies show that our proposed defenses significantly outperform well-knownbaseline defenses in mitigating five advanced Trojan attacks including tworecent state-of-the-art while being quite robust to small amounts of trainingdata and large-norm triggers.

Towards Effective and Robust Neural Trojan Defenses via Input Filtering