default search action
Maksym Andriushchenko
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c19]Linara Adilova, Maksym Andriushchenko, Michael Kamp, Asja Fischer
, Martin Jaggi:
Layer-wise linear mode connectivity. ICLR 2024 - [c18]Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion:
Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning. ICML 2024 - [i28]Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion:
Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning. CoRR abs/2402.04833 (2024) - [i27]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
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models. CoRR abs/2404.01318 (2024) - [i26]Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion:
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks. CoRR abs/2404.02151 (2024) - [i25]Javier Rando, Francesco Croce, Krystof Mitka, Stepan Shabalin, Maksym Andriushchenko, Nicolas Flammarion, Florian Tramèr:
Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs. CoRR abs/2404.14461 (2024) - [i24]Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion:
Is In-Context Learning Sufficient for Instruction Following in LLMs? CoRR abs/2405.19874 (2024) - [i23]Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, Rowan Wang, Zico Kolter, Matt Fredrikson, Dan Hendrycks:
Improving Alignment and Robustness with Circuit Breakers. CoRR abs/2406.04313 (2024) - [i22]Maksym Andriushchenko, Nicolas Flammarion:
Does Refusal Training in LLMs Generalize to the Past Tense? CoRR abs/2407.11969 (2024) - [i21]Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, Zico Kolter, Matt Fredrikson, Eric Winsor, Jerome Wynne, Yarin Gal, Xander Davies:
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents. CoRR abs/2410.09024 (2024) - 2023
- [c17]Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion:
A Modern Look at the Relationship between Sharpness and Generalization. ICML 2023: 840-902 - [c16]Maksym Andriushchenko, Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion:
SGD with Large Step Sizes Learns Sparse Features. ICML 2023: 903-925 - [c15]Maksym Andriushchenko, Dara Bahri, Hossein Mobahi, Nicolas Flammarion:
Sharpness-Aware Minimization Leads to Low-Rank Features. NeurIPS 2023 - [c14]Klim Kireev, Maksym Andriushchenko, Carmela Troncoso, Nicolas Flammarion:
Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings. NeurIPS 2023 - [i20]Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion:
A modern look at the relationship between sharpness and generalization. CoRR abs/2302.07011 (2023) - [i19]Maksym Andriushchenko, Dara Bahri, Hossein Mobahi, Nicolas Flammarion:
Sharpness-Aware Minimization Leads to Low-Rank Features. CoRR abs/2305.16292 (2023) - [i18]Klim Kireev, Maksym Andriushchenko, Carmela Troncoso, Nicolas Flammarion:
Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings. CoRR abs/2306.04064 (2023) - [i17]Maksym Andriushchenko, Francesco D'Angelo, Aditya Varre, Nicolas Flammarion:
Why Do We Need Weight Decay in Modern Deep Learning? CoRR abs/2310.04415 (2023) - [i16]Sungbin Shin, Dongyeop Lee, Maksym Andriushchenko, Namhoon Lee:
The Effects of Overparameterization on Sharpness-aware Minimization: An Empirical and Theoretical Analysis. CoRR abs/2311.17539 (2023) - [i15]Edoardo Debenedetti, Zishen Wan, Maksym Andriushchenko, Vikash Sehwag, Kshitij Bhardwaj, Bhavya Kailkhura:
Scaling Compute Is Not All You Need for Adversarial Robustness. CoRR abs/2312.13131 (2023) - 2022
- [c13]Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein:
Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks. AAAI 2022: 6437-6445 - [c12]Maksym Andriushchenko, Xiaoyang Rebecca Li, Geoffrey Oxholm, Thomas Gittings
ARIA: Adversarially Robust Image Attribution for Content Provenance. CVPR Workshops 2022: 33-43 - [c11]Maksym Andriushchenko, Nicolas Flammarion:
Towards Understanding Sharpness-Aware Minimization. ICML 2022: 639-668 - [c10]Klim Kireev, Maksym Andriushchenko, Nicolas Flammarion:
On the effectiveness of adversarial training against common corruptions. UAI 2022: 1012-1021 - [i14]Maksym Andriushchenko, Xiaoyang Rebecca Li, Geoffrey Oxholm, Thomas Gittings, Tu Bui, Nicolas Flammarion, John P. Collomosse:
ARIA: Adversarially Robust Image Attribution for Content Provenance. CoRR abs/2202.12860 (2022) - [i13]Maksym Andriushchenko, Nicolas Flammarion:
Towards Understanding Sharpness-Aware Minimization. CoRR abs/2206.06232 (2022) - [i12]Maksym Andriushchenko, Aditya Varre, Loucas Pillaud-Vivien, Nicolas Flammarion:
SGD with large step sizes learns sparse features. CoRR abs/2210.05337 (2022) - 2021
- [c9]Marius Mosbach, Maksym Andriushchenko, Dietrich Klakow:
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines. ICLR 2021 - [c8]Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein:
RobustBench: a standardized adversarial robustness benchmark. NeurIPS Datasets and Benchmarks 2021 - [i11]Klim Kireev, Maksym Andriushchenko, Nicolas Flammarion:
On the effectiveness of adversarial training against common corruptions. CoRR abs/2103.02325 (2021) - 2020
- [c7]Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein:
Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search. ECCV (23) 2020: 484-501 - [c6]Maksym Andriushchenko, Nicolas Flammarion:
Understanding and Improving Fast Adversarial Training. NeurIPS 2020 - [i10]Marius Mosbach, Maksym Andriushchenko, Dietrich Klakow:
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines. CoRR abs/2006.04884 (2020) - [i9]Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein:
Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks. CoRR abs/2006.12834 (2020) - [i8]Maksym Andriushchenko, Nicolas Flammarion:
Understanding and Improving Fast Adversarial Training. CoRR abs/2007.02617 (2020) - [i7]Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein:
RobustBench: a standardized adversarial robustness benchmark. CoRR abs/2010.09670 (2020)
2010 – 2019
- 2019
- [c5]Francesco Croce, Maksym Andriushchenko, Matthias Hein:
Provable Robustness of ReLU networks via Maximization of Linear Regions. AISTATS 2019: 2057-2066 - [c4]Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf:
Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem. CVPR 2019: 41-50 - [c3]Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf:
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. CVPR Workshops 2019: 58-74 - [c2]Maksym Andriushchenko, Matthias Hein:
Provably robust boosted decision stumps and trees against adversarial attacks. NeurIPS 2019: 12997-13008 - [i6]Maksym Andriushchenko, Matthias Hein:
Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks. CoRR abs/1906.03526 (2019) - [i5]Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein:
Square Attack: a query-efficient black-box adversarial attack via random search. CoRR abs/1912.00049 (2019) - 2018
- [i4]Francesco Croce, Maksym Andriushchenko, Matthias Hein:
Provable Robustness of ReLU networks via Maximization of Linear Regions. CoRR abs/1810.07481 (2018) - [i3]Marius Mosbach, Maksym Andriushchenko, Thomas Alexander Trost, Matthias Hein, Dietrich Klakow:
Logit Pairing Methods Can Fool Gradient-Based Attacks. CoRR abs/1810.12042 (2018) - [i2]Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf:
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. CoRR abs/1812.05720 (2018) - 2017
- [c1]Matthias Hein, Maksym Andriushchenko:
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation. NIPS 2017: 2266-2276 - [i1]Matthias Hein, Maksym Andriushchenko:
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation. CoRR abs/1705.08475 (2017)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-25 22:44 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: