Maksym Andriushchenko
Artificial Intelligence · 2017–2024
A researcher in the Science corpus: 12 papers; trusts 911 researchers and is trusted by 116 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 405 citations into it; #3,036 of 36,961 by trust here, #4,822 by citations
- Safety, Robustness & Interpretability — 224 citations into it; #177 of 2,259 by trust here, #515 by citations
- Computer Vision and Pattern Recognition — 132 citations into it; #6,232 of 21,973 by trust here, #6,852 by citations
- Signal Processing — 50 citations into it; #449 of 7,592 by trust here, #1,191 by citations
- Evaluation & Benchmarks — 38 citations into it
- Optimization & Training — 34 citations into it; #1,445 of 2,605 by trust here, #1,387 by citations
- Large Language Models — 32 citations into it; #322 of 810 by trust here, #570 by citations
- Hardware and Architecture — 31 citations into it; #36 of 1,731 by trust here, #295 by citations
Whom Maksym Andriushchenko trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Ian J. Goodfellow
- Geoffrey E. Hinton
- Christian Szegedy
- Diederik P. Kingma
- Yoshua Bengio
- Nicholas Carlini
- Ilya Sutskever
- Yann LeCun
Who trusts Maksym Andriushchenko overall
- Matthias Hein
- Francesco Croce
- Eric Wong
- Huan Zhang
- David Stutz
- Sven Gowal
- Sylvestre-Alvise Rebuffi
- Tianyu Pang
- Alexander Meinke
- Klas Leino
Papers from Maksym Andriushchenko's perspective
Ordered by how strongly the researchers Maksym Andriushchenko trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation (2017) — 553 citations
- Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem (2018) — 630 citations
- Provable Robustness of ReLU networks via Maximization of Linear Regions (2018) — 173 citations
- RobustBench: a standardized adversarial robustness benchmark (2020) — 928 citations
- Understanding and Improving Fast Adversarial Training (2020) — 353 citations
- Square Attack: a query-efficient black-box adversarial attack via random search (2019) — 1,300 citations
- Logit Pairing Methods Can Fool Gradient-Based Attacks (2018) — 87 citations
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents (2024) — 322 citations
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks (2024) — 544 citations
- Improving Alignment and Robustness with Circuit Breakers (2024) — 311 citations
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models (2024) — 556 citations
- On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines (2020) — 475 citations