AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

DRFGD: Disentangled Representation-Focused Generative Defense for Attack-Tolerant Cross-Modal Hashing

Zhongqing Yu, Xin Liu, Yiu-ming Cheung, Zhikai Hu, Wentao Fan, Pan Zhou

AAAI 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 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 divergence loss LDiv (ablation)DRFGD · FLICKR-25K I->T (CPAH, TA-DCH)MAP: 74.26 -> 74.85Improved
add classification loss LCls (ablation)DRFGD · FLICKR-25K I->T (CPAH, TA-DCH)MAP: 73.88 -> 74.85Improved
add alignment loss LAli (ablation)DRFGD · MS-COCO T->I (CPAH, TA-DCH)MAP: 49.79 -> 61.82Improved
add alignment loss LAli (ablation)DRFGD · FLICKR-25K T->I (CPAH, TA-DCH)MAP: 67.83 -> 74.70Improved
add reconstruction loss LRec (ablation)DRFGD · MS-COCO T->I (CPAH, TA-DCH)MAP: 43.95 -> 61.82Improved
add reconstruction loss LRec (ablation)DRFGD · FLICKR-25K T->I (CPAH, TA-DCH)MAP: 61.19 -> 74.70Improved
add discrimination loss LDis (ablation)DRFGD · NUS-WIDE T->I (CPAH, TA-DCH)MAP: 64.90 -> 66.58Improved
use DRFGD instead of best baseline defenseDADH, EQB2A · FLICKR-25K I->TMAP: 70.13 -> 72.06Improved
use DRFGD under targeted TA-DCH attackDADH · I->T retrievalMAP: 1.81%, 4.10%, 1.60%Improved
use DRFGD instead of baselines for t-MAPDAPH · I->Tt-MAP: 2.23%, 1.67%, 2.40% reductionImproved
use DRFGD instead of other defenses on benign dataDAPH · FLICKR-25K I->T benignMAP: 83.42 -> 84.61Improved
use adversarial training defenses (vs DRFGD) on benign queriesATRDH/SAAT · FLICKR-25K I->T benign (CPAH)MAP: 75.76 -> 82.53Hurt

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