Your Out-of-Distribution Detection Method is Not Robust!
arxiv.org · 8,009 words · saved by 1 readers
N/A
Your Out-of-Distribution Detection Method is Not Robust! Mohammad Azizmalayeri, Arshia Soltani Moakhar, Arman Zarei, Reihaneh Zohrabi, Mohammad Taghi Manzuri, Mohammad Hossein Rohban arXiv:2209.15246v1 [cs.CV] 30 Sep 2022 Department of Computer Engineering Sharif University of…
saved by
related reading
- Deep Anomaly Detection with Outlier Exposurearxiv.org
- [2003.01690] Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacksarxiv.org
- Adversarial Examples Are Not Bugs, They Are Features – gradient sciencegradientscience.org
- Announcing Safety Research Grantsthinkingmachines.ai
- On Getting Confidence Estimates from Neural Networks | Bharath's notesbharathpbhat.github.io
- [1610.00768] Technical Report on the CleverHans v2.1.0 Adversarial Examples Libraryarxiv.org
- [2602.04899] Phantom Transfer: Data-level Defences are Insufficient Against Data Poisoningarxiv.org
- Some Lessons from Adversarial Machine Learning | FAR.AIfar.ai
- A gentle introduction to mechanistic anomaly detection — LessWronglesswrong.com
- Solving adversarial attacks in computer vision as a baby version of general AI alignment | Stanislav Fortstanislavfort.com
- Cost-Effective Constitutional Classifiers via Representation Re-usealignment.anthropic.com
- ICCV 2023 Open Access Repositoryopenaccess.thecvf.com