α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Maksym Andriushchenko
Maksym Andriushchenko
1
Affiliations
Affiliations
EPFL
9
papers
2,120
total citations
papers (9)
Square Attack: a query-efficient black-box adversarial attack via random search
ECCV 2020
arXiv
1,191
citations
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
ICLR 2025
arXiv
401
citations
Understanding and Improving Fast Adversarial Training
NEURIPS 2020
arXiv
335
citations
Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
ICML 2024
arXiv
88
citations
Sharpness-Aware Minimization Leads to Low-Rank Features
NEURIPS 2023
arXiv
36
citations
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
NEURIPS 2025
arXiv
25
citations
Is In-Context Learning Sufficient for Instruction Following in LLMs?
ICLR 2025
arXiv
22
citations
Layer-wise linear mode connectivity
ICLR 2024
arXiv
20
citations
Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings
NEURIPS 2023
arXiv
2
citations