Maksym Andriushchenko

According to our database, Maksym Andriushchenko authored at least 29 papers between 2017 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Does Refusal Training in LLMs Generalize to the Past Tense?

Maksym Andriushchenko, Nicolas Flammarion

CoRR, 2024

Improving Alignment and Robustness with Circuit Breakers.

Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, Rowan Wang, Zico Kolter, Matt Fredrikson, Dan Hendrycks

CoRR, 2024

Is In-Context Learning Sufficient for Instruction Following in LLMs?

Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

CoRR, 2024

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs.

Javier Rando, Francesco Croce, Krystof Mitka, Stepan Shabalin, Maksym Andriushchenko, Nicolas Flammarion, Florian Tramèr

CoRR, 2024

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

CoRR, 2024

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramèr, Hamed Hassani, Eric Wong

CoRR, 2024

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning.

Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Layer-wise linear mode connectivity.

Linara Adilova, Maksym Andriushchenko, Michael Kamp, Asja Fischer, Martin Jaggi

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Scaling Compute Is Not All You Need for Adversarial Robustness.

Edoardo Debenedetti, Zishen Wan, Maksym Andriushchenko, Vikash Sehwag, Kshitij Bhardwaj, Bhavya Kailkhura

CoRR, 2023

The Effects of Overparameterization on Sharpness-aware Minimization: An Empirical and Theoretical Analysis.

Sungbin Shin, Dongyeop Lee, Maksym Andriushchenko, Namhoon Lee

CoRR, 2023

Why Do We Need Weight Decay in Modern Deep Learning?

Maksym Andriushchenko, Francesco D'Angelo, Aditya Varre, Nicolas Flammarion

CoRR, 2023

Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings.

Klim Kireev, Maksym Andriushchenko, Carmela Troncoso, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Sharpness-Aware Minimization Leads to Low-Rank Features.

Maksym Andriushchenko, Dara Bahri, Hossein Mobahi, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

SGD with Large Step Sizes Learns Sparse Features.

Maksym Andriushchenko, Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion

Proceedings of the International Conference on Machine Learning, 2023

A Modern Look at the Relationship between Sharpness and Generalization.

Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion

Proceedings of the International Conference on Machine Learning, 2023

2022

On the effectiveness of adversarial training against common corruptions.

Klim Kireev, Maksym Andriushchenko, Nicolas Flammarion

Proceedings of the Uncertainty in Artificial Intelligence, 2022

Towards Understanding Sharpness-Aware Minimization.

Maksym Andriushchenko, Nicolas Flammarion

Proceedings of the International Conference on Machine Learning, 2022

ARIA: Adversarially Robust Image Attribution for Content Provenance.

Maksym Andriushchenko, Xiaoyang Rebecca Li, Geoffrey Oxholm, Thomas Gittings, Tu Bui, Nicolas Flammarion, John P. Collomosse

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022

Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks.

Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

RobustBench: a standardized adversarial robustness benchmark.

Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein

Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines.

Marius Mosbach, Maksym Andriushchenko, Dietrich Klakow

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

RobustBench: a standardized adversarial robustness benchmark.

Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein

CoRR, 2020

Understanding and Improving Fast Adversarial Training.

Maksym Andriushchenko, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search.

Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein

Proceedings of the Computer Vision - ECCV 2020, 2020

2019

Provably robust boosted decision stumps and trees against adversarial attacks.

Maksym Andriushchenko, Matthias Hein

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem.

Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Provable Robustness of ReLU networks via Maximization of Linear Regions.

Francesco Croce, Maksym Andriushchenko, Matthias Hein

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Logit Pairing Methods Can Fool Gradient-Based Attacks.

Marius Mosbach, Maksym Andriushchenko, Thomas Alexander Trost, Matthias Hein, Dietrich Klakow

CoRR, 2018

2017

Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation.

Matthias Hein, Maksym Andriushchenko

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017