--- title: NDSS 2025 – NDSS 2025 – BARBIE: Robust Backdoor... description: BARBIE is a backdoor detection method for deep learning models presented at NDSS 2025. It introduces a novel latent separability metric called Relative... canonical: https://daily.dev/posts/ndss-2025-ndss-2025-barbie-robust-backdoor-detection-based-on-latent-separability-cbtu3peb0 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: NDSS 2025 – NDSS 2025 – BARBIE: Robust Backdoor Detection Based On Latent Separability | daily.dev og:description: BARBIE is a backdoor detection method for deep learning models presented at NDSS 2025. It introduces a novel latent separability metric called Relative... og:url: https://daily.dev/posts/ndss-2025-ndss-2025-barbie-robust-backdoor-detection-based-on-latent-separability-cbtu3peb0 og:image: https://api.daily.dev/og/posts/CBTU3pEb0.png og:image:alt: NDSS 2025 – NDSS 2025 – BARBIE: Robust Backdoor Detection Based On Latent Separability og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # NDSS 2025 – NDSS 2025 – BARBIE: Robust Backdoor Detection Based On Latent Separability **[Security Boulevard](https://daily.dev/sources/securityboulevard)** · 1 min read · 1 upvotes · 0 comments ## Summary BARBIE is a backdoor detection method for deep learning models presented at NDSS 2025. It introduces a novel latent separability metric called Relative Competition Score (RCS), which characterizes the dominance of latent representations over model output. Unlike existing approaches that rely on clustering or distance computation—making them vulnerable to adaptive attacks—BARBIE inverts two sets of latent representations per label without requiring access to benign or backdoored samples. Evaluated on over 10,000 models across 4 datasets against 14 backdoor attack types, BARBIE improves true positive rates by 17–43% over 7 baselines while maintaining lower false positive rates. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [NDSS 2025 – A Method To Facilitate Membership Inference Attacks In Deep Learning Models](https://daily.dev/posts/ndss-2025-a-method-to-facilitate-membership-inference-attacks-in-deep-learning-models-8y407qiao) · Security Boulevard · 0 upvotes · 0 comments - [NDSS 2025 – CLIBE: Detecting Dynamic Backdoors In Transformer-based NLP Models](https://daily.dev/posts/ndss-2025-clibe-detecting-dynamic-backdoors-in-transformer-based-nlp-models-b8wcrtkb4) · Security Boulevard · 0 upvotes · 0 comments - [NDSS 2025 – LADDER: Multi-Objective Backdoor Attack Via Evolutionary Algorithm](https://daily.dev/posts/ndss-2025-ladder-multi-objective-backdoor-attack-via-evolutionary-algorithm-8kxtleiwy) · Security Boulevard · 0 upvotes · 0 comments - [NDSS 2025 – Defending Against Backdoor Attacks On Graph Neural Networks Via Discrepancy Learning](https://daily.dev/posts/ndss-2025-defending-against-backdoor-attacks-on-graph-neural-networks-via-discrepancy-learning-6swnofjpb) · Security Boulevard · 0 upvotes · 0 comments - [NDSS 2025 – Black-Box Membership Inference Attacks Against Fine-Tuned Diffusion Models](https://daily.dev/posts/ndss-2025-black-box-membership-inference-attacks-against-fine-tuned-diffusion-models-o1v1us0md) · Security Boulevard · 0 upvotes · 0 comments --- Tags: [#cyber](https://daily.dev/tags/cyber), [#deep-learning](https://daily.dev/tags/deep-learning) [View this post on daily.dev](https://daily.dev/posts/ndss-2025-ndss-2025-barbie-robust-backdoor-detection-based-on-latent-separability-cbtu3peb0) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"NDSS 2025 – NDSS 2025 – BARBIE: Robust Backdoor Detection Based On Latent Separability","url":"https://daily.dev/posts/ndss-2025-ndss-2025-barbie-robust-backdoor-detection-based-on-latent-separability-cbtu3peb0","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ndss-2025-ndss-2025-barbie-robust-backdoor-detection-based-on-latent-separability-cbtu3peb0"},"datePublished":"2026-02-19T20:33:34.923Z","dateModified":"2026-02-19T20:33:54.500Z","description":"BARBIE is a backdoor detection method for deep learning models presented at NDSS 2025. It introduces a novel latent separability metric called Relative...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8fe9eeb967de205fd6743e2535f16178?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8fe9eeb967de205fd6743e2535f16178?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Security Boulevard","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Security Boulevard","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/3613c832180040de8d85bb29f74395be","url":"https://daily.dev/sources/securityboulevard"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ndss-2025-ndss-2025-barbie-robust-backdoor-detection-based-on-latent-separability-cbtu3peb0","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"cyber,deep-learning","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Security Boulevard","item":"https://daily.dev/sources/securityboulevard"},{"@type":"ListItem","position":3,"name":"NDSS 2025 – NDSS 2025 – BARBIE: Robust Backdoor Detection Based On Latent Separability"}]} ```