Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Related papers for robust machine learning
| Date | Stars |
|---|---|
| 2026-07-31 | 562 |
| 2026-08-05 | 562 |
| 2026-08-06 | 562 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Papers-of-Robust-ML Related papers for robust machine learning (we mainly focus on defenses). # Statement Since there are tens of new papers on adversarial defense in each conference, we are only able to update those we just read and consider as insightful. Anyone is welcomed to submit a pull request for the related and unlisted papers on adversarial defense, which are pulished on peer-review conferences (ICML/NeurIPS/ICLR/CVPR etc.) or released on arXiv. ## Contents - <a href="#General_training">General Defenses (training phase)</a><br> - <a href="#General_inference">General Defenses (inference phase)</a><br> - <a href="#Detection">Adversarial Detection</a><br> - <a href="#Certified Defense and Model Verification">Certified Defense and Model Verification</a><br> - <a href="#Theoretical">Theoretical Analysis</a><br> - <a href="#Empirical">Empirical Analysis</a><br> - <a href="#Beyond_Safety">Beyond Safety (Adversarial for Good)</a><br> - <a href="#Seminal_work">Seminal Work</a><br> - <a href="#Benchmark_Datasets">Benchmark Datasets</a><br> <a id='General_training'></a> ## General Defenses (training phase) * [Better Diffusion Models Further Improve Adversarial Training](https://arxiv.org/pdf/2302.04638.pdf) (ICML 2023) <br/> This paper advocate that better diffusion models such as EDM can further improve adversarial training beyond using DDPM, which achieves new state-of-the-art performance on CIFAR-10/100 as listed on RobustBench. * [FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740036.pdf) (ECCV 2022) <br/> This paper proposes a novel aliasing-free downsampling layer to prevent catastrophic overfitting during simple Fast Gradient Sign Method (FGSM) adversarial training. * [Robustness and Accuracy Could Be Reconcilable by (Proper) Definition](https://arxiv.org/pdf/2202.10103.pdf) (ICML 2022) <br/> This paper advocate that robustness and accuracy are not at odds, as long as we slightly modify the definition of robust error. Efficient ways of optimizating the new SCORE objective is provided. * [Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks](https://openreview.net/pdf?id=9CPc4EIr2t1) (NeurIPS 2021) <br/> This paper combines the stable conditions in control theory into neural ODE to induce locally stable models. * [Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart ](https://arxiv.org/pdf/2105.14785.pdf) (CVPR 2022) <br/> This paper proposes a coupling rejection strategy, where two simple but well-designed rejection metrics can be coupled to provabably distinguish any misclassified sample from correclty classified ones. * [Fixing Data Augmentation to Improve Adversarial Robustness](https://arxiv.org/pdf/2103.01946.pdf) (NeurIPS 2021) <br/> This paper shows that after applying weight moving average, data augmentation (either by transformatons or generative models) can further improve robustness of adversarial training. * [Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?](https://arxiv.org/pdf/2104.09425.pdf) (ICLR 2022) <br/> This paper verifies that leveraging more data sampled from a (high-quality) generative model that was trained on the same dataset (e.g., CIFAR-10) can still improve robustness of adversarially trained models, without using any extra data. * [Towards Robust Neural Networks via Close-loop Control](https://openreview.net/forum?id=2AL06y9cDE-) (ICLR 2021) <br/> This paper introduce a close-loop control framework to enhance adversarial robustness of trained networks. * [Understanding and Improving Fast Adversarial Training](https://arxiv.org/pdf/2007.02617.pdf) (NeurIPS 2020) <br/> A systematic study of catastrophic overfitting in adversarial training, its reasons, and ways of resolving it. The proposed regularizer, *GradAlign*, helps to prevent catastrophic overfitting and scale FGSM training to
Excerpt of 33,177 characters
Read on GitHub
111
Maksym Andriushchenko · ELLIS Institute Tübingen
5
4
2
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:dd6ede7c7be57fbd, llm:description: 'Related papers for robust machine learning' (repository description)
matched fp:dd6ede7c7be57fbd, llm:description: 'Related papers for robust machine learning' (repository description)
matched fp:dd6ede7c7be57fbd, llm:description: 'Related papers for robust machine learning' (repository description)