AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Defending from GeoLocalization through Adversarial Road Trips

Niccolò Niccoli, Federico Becattini, Lorenzo Seidenari

ECCV 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 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
replace PGD with RoadTrip beam search over intermediate geographic targetsGeoCLIP attack · Im2GPS3k eps 2/255ACC_GT@2500km: 8.34% -> 1.03%Improved
replace PGD with RoadTripGeoCLIP attack · Im2GPS3k eps 2/255ACC_Target@1km: 71.81% -> 93.43%Improved
replace PGD with RoadTripGeoCLIP attack · YFCC4k eps 2/255ACC_GT@2500km: 4.23% -> 1.19%Improved
replace PGD with RoadTrip at larger budgetGeoCLIP attack · Im2GPS3k eps 4/255ACC_GT@2500km: 1.27% -> 0.73%Improved
use RTA instead of five-start parallel PGD (multi-start) (ablation)PGD · Im2GPS3k eps 2/255ACC_GT@2500km: 5.41% -> 1.03%Improved
use RTA instead of random restart PGD (ablation)PGD · Im2GPS3k eps 2/255ACC_Target@1km: 64.27% -> 93.43%Improved
use adaptive sampled intermediate targets instead of fixed interpolated targets (ablation)PGD · Im2GPS3k eps 2/255ACC_Target@1km: 32.13% -> 93.43%Improved
random restart added to PGD (ablation)PGD · Im2GPS3k eps 2/255ACC_Target@1km: 71.81% -> 64.27%Hurt
interpolated intermediate targets added to PGD (ablation)PGD · Im2GPS3k eps 2/255ACC_GT@2500km: 8.34% -> 13.77%Hurt
use RTA instead of GeoShield (transfer to Img2Loc)attack · Im2GPS3k Img2Loc eps 2/255ACC_GT@2500km: 63.43% -> 27.86%Improved
use RTA instead of GeoShield (transfer to G3)attack · Im2GPS3k G3 eps 2/255ACC_GT@2500km: 78.14% -> 19.12%Improved
use RTA instead of GeoShield on perceptual qualityattack · Im2GPS3k eps 16/255LPIPS: 0.305 -> 0.174Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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