Folgen
Maksym Andriushchenko
Maksym Andriushchenko
Postdoctoral Researcher at EPFL
Bestätigte E-Mail-Adresse bei epfl.ch - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Square attack: a query-efficient black-box adversarial attack via random search
M Andriushchenko*, F Croce*, N Flammarion, M Hein
ECCV 2020, 2020
11422020
RobustBench: a standardized adversarial robustness benchmark
F Croce*, M Andriushchenko*, V Sehwag*, E Debenedetti*, N Flammarion, ...
NeurIPS 2021 Datasets and Benchmarks Track, Best Paper Honorable Mention …, 2021
7792021
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem
M Hein, M Andriushchenko, J Bitterwolf
CVPR 2019 (oral), 2019
6662019
Formal guarantees on the robustness of a classifier against adversarial manipulation
M Hein, M Andriushchenko
NeurIPS 2017, 2017
6372017
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
M Mosbach, M Andriushchenko, D Klakow
ICLR 2021, 2021
4292021
Understanding and Improving Fast Adversarial Training
M Andriushchenko, N Flammarion
NeurIPS 2020, 2020
3602020
Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks
M Andriushchenko, M Hein
NeurIPS 2019, 2019
3072019
Provable Robustness of ReLU Networks via Maximization of Linear Regions
F Croce*, M Andriushchenko*, M Hein
AISTATS 2019, 2019
1902019
Towards Understanding Sharpness-Aware Minimization
M Andriushchenko, N Flammarion
ICML 2022, 2022
1582022
On the effectiveness of adversarial training against common corruptions
K Kireev*, M Andriushchenko*, N Flammarion
UAI 2022, 2021
1192021
Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks
F Croce, M Andriushchenko, ND Singh, N Flammarion, M Hein
AAAI 2022, 2022
1152022
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
M Andriushchenko, F Croce, N Flammarion
ICLR 2025, 2025
942025
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
P Chao*, E Debenedetti*, A Robey*, M Andriushchenko*, F Croce, ...
NeurIPS 2024 Datasets and Benchmarks Track, 2024
932024
Logit Pairing Methods Can Fool Gradient-Based Attacks
M Mosbach*, M Andriushchenko*, T Trost, M Hein, D Klakow
NeurIPS 2018 Workshop on Security in Machine Learning, 2018
842018
SGD with Large Step Sizes Learns Sparse Features
M Andriushchenko, A Varre, L Pillaud-Vivien, N Flammarion
ICML 2023, 2022
612022
Improving Alignment and Robustness with Circuit Breakers
A Zou, L Phan, J Wang, D Duenas, M Lin, M Andriushchenko, R Wang, ...
NeurIPS 2024, 2024
60*2024
A Modern Look at the Relationship between Sharpness and Generalization
M Andriushchenko, F Croce, M Müller, M Hein, N Flammarion
ICML 2023, 2023
552023
Sharpness-Aware Minimization Leads to Low-Rank Features
M Andriushchenko, D Bahri, H Mobahi, N Flammarion
NeurIPS 2023, 2023
272023
Long is more for alignment: A simple but tough-to-beat baseline for instruction fine-tuning
H Zhao, M Andriushchenko, F Croce, N Flammarion
ICML 2024, 2024
262024
Why Do We Need Weight Decay in Modern Deep Learning?
F D'Angelo*, M Andriushchenko*, A Varre, N Flammarion
NeurIPS 2024, 2024
232024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20