Skip to content

Maksym Andriushchenko

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

18

Venues

7

Active years

2019–2025

Best venue rank

A*

Where they publish

Papers

18 indexed papers, newest first.

YearVenueTitleAuthors
2025ICLRJailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2025ICLRDoes Refusal Training in LLMs Generalize to the Past Tense?Maksym Andriushchenko, Nicolas Flammarion
2025ICLRAgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, J. Zico Kolter, Matt Fredrikson, Yarin Gal, Xander Davies
2025ICLRIs In-Context Learning Sufficient for Instruction Following in LLMs?Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2025UAICritical Influence of Overparameterization on Sharpness-aware Minimization.Sungbin Shin, Dongyeop Lee, Maksym Andriushchenko, Namhoon Lee
2024ICLRLayer-wise linear mode connectivity.Linara Adilova, Maksym Andriushchenko, Michael Kamp, Asja Fischer, Martin Jaggi
2024ICMLLong Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning.Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2023ICMLA Modern Look at the Relationship between Sharpness and Generalization.Maksym Andriushchenko, Francesco Croce, Maximilian Mller, Matthias Hein, Nicolas Flammarion
2023ICMLSGD with Large Step Sizes Learns Sparse Features.Maksym Andriushchenko, Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion
2022AAAISparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks.Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein
2022CVPRARIA: Adversarially Robust Image Attribution for Content Provenance.Maksym Andriushchenko, Xiaoyang Rebecca Li, Geoffrey Oxholm, Thomas Gittings, Tu Bui, Nicolas Flammarion, John P. Collomosse
2022ICMLTowards Understanding Sharpness-Aware Minimization.Maksym Andriushchenko, Nicolas Flammarion
2022UAIOn the effectiveness of adversarial training against common corruptions.Klim Kireev, Maksym Andriushchenko, Nicolas Flammarion
2021ICLROn the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines.Marius Mosbach, Maksym Andriushchenko, Dietrich Klakow
2020ECCVSquare Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search.Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein
2019AISTATSProvable Robustness of ReLU networks via Maximization of Linear Regions.Francesco Croce, Maksym Andriushchenko, Matthias Hein
2019CVPRWhy ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem.Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf
2019CVPRWhy ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem.Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf