Research map / Adversarial robustness and security / Certified and empirical robustness
Adversarially robust learning for security-constrained optimal power flow
Priya L. Donti, Aayushya Agarwal, Neeraj Vijay Bedmutha, Larry Pileggi, J Zico Kolter
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 |
|---|---|---|---|
| use CANdY N-3 SCOPF instead of base-case OPF | base OPF dispatch · 4622-node N-2 and N-3 contingencies | violations: 3-4x fewer | Improved |
| use CANdY instead of PowerModels N-1 SCOPF | PowerModels N-1 SCOPF · 4622-node N-3 contingencies | violations: 5x fewer | Improved |
| use CANdY instead of PowerModels N-1 SCOPF | PowerModels N-1 SCOPF · 4622-node N-1 and N-2 contingencies | violations | No clear effect |
| use CANdY (k=1) vs top GO Challenge 1 entries | GO Challenge 1 submissions · 5K network N-1 SCOPF | score: 552,032 vs 545,783-553,328 | No clear effect |
| increase attack budget k from 1 to 3 | CANdY · 4622-node SCOPF | iterations to converge | No clear effect |
| use implicit-gradient attack instead of linear approximation | contingency search · IEEE 14-node N-2 | loss: 3 | Improved |
Closest papers by meaning
- PF∆: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations (NeurIPS 2025 · similarity 0.84)
- A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization (ICLR 2025 · similarity 0.84)
- Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs (ICML 2025 · similarity 0.83)
- Enhancing Adversarial Robustness in SNNs with Sparse Gradients (ICML 2024 · similarity 0.83)
- Re-thinking Data Availability Attacks Against Deep Neural Networks (CVPR 2024 · similarity 0.83)
- E2E-AT: A Unified Framework for Tackling Uncertainty in Task-Aware End-to-End Learning (AAAI 2024 · similarity 0.83)
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.
