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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| increase attack budget C from 0.25 to 2.0 | Gradient attack on AR learner · target distance r1=1.294 (mean) | attacker loss: 0.393 -> 0.294 | Improved |
| increase attack budget C from 0.25 to 2.0 | Gradient attack on AR learner · target distance r2=1.399 (mean) | attacker loss: 0.573 -> 0.446 | Improved |
| increase attack budget C from 0.25 to 2.0 | Gradient attack on AR learner · target distance r3=1.514 (mean) | attacker loss: 0.722 -> 0.580 | Improved |
| increase target distance from r1 to r2 to r3 | Gradient attack on AR learner · C=0.25 (mean) | attacker loss: 0.393 -> 0.573 -> 0.722 | Hurt |
| increase target distance from r1 to r3 | Gradient attack on AR learner · C=2.0 (mean) | attacker loss: 0.294 -> 0.580 | Hurt |
| increase attack budget beyond C1 to C4 | Gradient attack on AR learner · loss tapering off | attacker loss: 0.393 -> 0.294 | No clear effect |
| small perturbation C1=0.25 shifts learned model | Gradient attack on AR learner · r1 target | shift of learned model: .911 | Improved |
Closest papers by meaning
- Attacks on Online Learners: a Teacher-Student Analysis (NeurIPS 2023 · similarity 0.86)
- Improving Robustness to Model Inversion Attacks via Mutual Information Regularization (AAAI 2021 · similarity 0.86)
- Adversarial Attack and Defense for Machine Learning in Statistical Physics (NeurIPS 2026 · similarity 0.85)
- Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable (NeurIPS 2024 · similarity 0.84)
- Adversarial Machine Unlearning (ICLR 2025 · similarity 0.84)
- Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization (NeurIPS 2024 · similarity 0.84)
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.
