AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

"SIMBA: Split Inference - Mechanisms, Benchmarks and Attacks"

Abhishek Singh, Vivek Sharma, Rohan Sukumaran, John J Mose, Jeffrey K Chiu, Justin Yu, Ramesh Raskar

ECCV 2024 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 4 citations (OpenAlex)

Read the paper

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
use data-driven obfuscation instead of data-independent noise or blurobfuscation mechanisms · privacy-utility trade-off on image classificationprivacy-utility trade-offImproved
split the network at a deeper layer (ablation)reconstruction attacks on ResNet-18 activations · CelebA and UTKFacereconstruction quality (SSIM)Hurt
use model-space/input-space optimization attack (A.2) instead of learned inversion (A.1)feature inversion attack · ResNet-18 split layersreconstruction qualityMixed
give the attacker a larger share of training data (ablation)attack A.1 · UTKFace, various split layersreconstruction qualityImproved
train the attacker on a different face dataset (distribution shift) (ablation)attack A.1 · FairFace to UTKFace, fifth split layerreconstruction qualityNo clear effect

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