AI Paper Atlas

Research map / Time series / Causal and generative time series

Attacking Data Transforming Learners at Training Time

Scott Alfeld, Ara Vartanian, Lucas Newman-Johnson, Benjamin I.P. Rubinstein

AAAI 2019 · Time series › Causal and generative time series · approach: Dynamical system reconstruction · 2 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
increase attack budget C from 0.25 to 2.0Gradient attack on AR learner · target distance r1=1.294 (mean)attacker loss: 0.393 -> 0.294Improved
increase attack budget C from 0.25 to 2.0Gradient attack on AR learner · target distance r2=1.399 (mean)attacker loss: 0.573 -> 0.446Improved
increase attack budget C from 0.25 to 2.0Gradient attack on AR learner · target distance r3=1.514 (mean)attacker loss: 0.722 -> 0.580Improved
increase target distance from r1 to r2 to r3Gradient attack on AR learner · C=0.25 (mean)attacker loss: 0.393 -> 0.573 -> 0.722Hurt
increase target distance from r1 to r3Gradient attack on AR learner · C=2.0 (mean)attacker loss: 0.294 -> 0.580Hurt
increase attack budget beyond C1 to C4Gradient attack on AR learner · loss tapering offattacker loss: 0.393 -> 0.294No clear effect
small perturbation C1=0.25 shifts learned modelGradient attack on AR learner · r1 targetshift of learned model: .911Improved

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