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

Adversaries can embed backdoors in deep learning models by introducingbackdoor poison samples into training datasets. In this work, we investigatehow to detect such poison samples to mitigate the threat of backdoor attacks.First, we uncover a post-hoc workflow underlying most prior work, wheredefenders passively allow the attack to proceed and then leverage thecharacteristics of the post-attacked model to uncover poison samples. We revealthat this workflow does not fully exploit defenders' capabilities, and defensepipelines built on it are prone to failure or performance degradation in manyscenarios. Second, we suggest a paradigm shift by promoting a proactive mindsetin which defenders engage proactively with the entire model training and poisondetection pipeline, directly enforcing and magnifying distinctivecharacteristics of the post-attacked model to facilitate poison detection.Based on this, we formulate a unified framework and provide practical insightson designing detection pipelines that are more robust and generalizable. Third,we introduce the technique of Confusion Training (CT) as a concreteinstantiation of our framework. CT applies an additional poisoning attack tothe already poisoned dataset, actively decoupling benign correlation whileexposing backdoor patterns to detection. Empirical evaluations on 4 datasetsand 14 types of attacks validate the superiority of CT over 14 baselinedefenses.

Towards A Proactive ML Approach for Detecting Backdoor Poison Samples