AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Breaking High Confidence: Practical Face Impersonation under High-Security Thresholds

Changjin Kim, Seunghun Paik, Dongsoo Kim, Jae Hong Seo

ECCV 2026 · Adversarial robustness and security › Backdoor and poisoning · approach: Backdoors in large multimodal models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add correction matrix (ablation)NbNet attack · LFW vs AWS CompareFace (threshold 99)ASR (%): 0.33 -> 2.83Improved
add PCA-based OFS (ablation)NbNet attack · LFW vs AWS CompareFace (threshold 99)ASR (%): 0.33 -> 46.68Improved
add correction matrix on top of PCA-based OFS (ablation)NbNet+P · LFW vs AWS CompareFace (threshold 99)ASR (%): 46.68 -> 56.10Improved
replace NbNet with SPNet inverse model (ablation)NbNet+CP · LFW vs AWS CompareFace (threshold 99)ASR (%): 56.10 -> 92.80Improved
replace SPNet with Arc2Face high-resolution inverse model (ablation)SPNet+CP · LFW vs AWS CompareFace (threshold 99)ASR (%): 92.80 -> 53.92Hurt
add micro-level modifications (GELU, no tanh, PNorm, tuning) to NbNet (ablation)NbNet inverse model · LFW inverse model ablationinversion precision: 0.8809 -> 0.9687Improved
add micro-level modifications to NbNet (ablation)NbNet inverse model · LFW vs AWS CompareFace (threshold 99)ASR (%): 56.10 -> 91.41 ± 1.75Improved
add DSCasConv on top of micro modifications (ablation)SPNet · LFW vs AWS CompareFace (threshold 99)ASR (%): 91.41 ± 1.75 -> 91.88 ± 1.60Improved
add correction matrix on top of PCA-based OFS (ablation)NbNet+P · LFW, F_1, FMR 1e-6ASR (%): 10.37 -> 11.47Improved
add correction matrix alone (ablation)NbNet baseline · LFW, F_2, FMR 1e-6ASR (%): 24.13 -> 22.20Hurt
add PCA-based OFS (ablation)NbNet baseline · LFW, F_2, FMR 1e-6ASR (%): 24.13 -> 69.13Improved
add PCA-based OFS (ablation)NbNet baseline · LFW, F_S (white-box), FMR 1e-6ASR (%): 16.77 -> 43.47Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy