AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for Deep Neural Networks

Abhishek Singh, Ayush Chopra, Ethan Garza, Emily Zhang, Praneeth Vepakomma, Vivek Sharma, Ramesh Raskar

CVPR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 43 citations (OpenAlex)

Check 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
Use dynamic channel pruning to obfuscate sensitive activationsDISCO · CIFAR-10 sensitive attribute leakagesensitive-attribute adversary accuracy: 0.3573 -> 0.2282Improved
Use dynamic channel pruning to obfuscate sensitive activationsDISCO · CelebA reconstructionSSIM: 0.68 -> 0.38Improved
Use dynamic channel pruning to obfuscate sensitive activationsDISCO · CelebA reconstructionPSNR: 20.49 -> 11.61Improved
Add the spatial-decoupling pre-processing module (ablation)DISCO · Sensitive-input reconstructionreconstruction qualityImproved
Turn off the pre-processing module (ablation)DISCO · Sensitive-input reconstruction with supervised decoderreconstruction qualityMixed
Use Gaussian activation noise strong enough to prevent reconstructionCollaborative inference · Sensitive-input reconstructiontask utilityHurt
Protect Big Nose instead of Mouth Open while predicting SmilingDISCO · CelebAsensitive-attribute adversary accuracy: 0.783 -> 0.559Improved
Protect Mouth Open instead of Big Nose while predicting SmilingDISCO · CelebAsensitive-attribute adversary accuracy: 0.814 -> 0.783Mixed

Later papers that compared with this method

3 later accepted papers report DisCo as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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