← Authors

Maksym Andriushchenko

24 papers · 2017–2025 · 8 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (8) 🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (27) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown 🀝 Dynamic Duo (15) πŸ† Grand Slam πŸ—ƒοΈ Keyword Collector (86) πŸ’Ž Century Club (24) ⚑ Prolific Year (5) πŸ”₯ Unstoppable (7) ❓ The Questioner (3) πŸ“ˆ Trend Setter

Conferences

NIPS (8) ICLR (6) ICML (4) UAI (2) AAAI (1) AISTATS (1) CVPR (1) ECCV (1)

Top co-authors

Nicolas Flammarion (15) Francesco Croce (8) Matthias Hein (7) Klim Kireev (2) Derek Duenas (2) Dan Hendrycks (2) Matt Fredrikson (2) Maxwell Lin (2) Justin Wang (2) Andy Zou (2)

Keywords

adversarial robustness (6) adversarial attack (4) neural network (4) adversarial training (3) adversarial learning (2) sharpness-aware minimization (2) stochastic gradient descent (2) neural network robustness (2) boosted decision tree (2) ai safety (2) implicit regularization (2) robust optimization (1) confidence calibration (1) data augmentation (1) image classification (1) sparse representation (1) formal verification (1) black-box optimization (1) benchmark evaluation (1) out-of-distribution generalization (1)

Papers

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks ICLR 2025
Critical Influence of Overparameterization on Sharpness-aware Minimization UAI 2025
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents ICLR 2025
Is In-Context Learning Sufficient for Instruction Following in LLMs? ICLR 2025
Does Refusal Training in LLMs Generalize to the Past Tense? ICLR 2025
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models NIPS 2024
Improving Alignment and Robustness with Circuit Breakers NIPS 2024
Layer-wise linear mode connectivity ICLR 2024
Why Do We Need Weight Decay in Modern Deep Learning? NIPS 2024
Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning ICML 2024
Sharpness-Aware Minimization Leads to Low-Rank Features NIPS 2023
SGD with Large Step Sizes Learns Sparse Features ICML 2023
A Modern Look at the Relationship between Sharpness and Generalization ICML 2023
Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings NIPS 2023
On the effectiveness of adversarial training against common corruptions UAI 2022
Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks AAAI 2022
Towards Understanding Sharpness-Aware Minimization ICML 2022
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines ICLR 2021
Square Attack: a query-efficient black-box adversarial attack via random search ECCV 2020
Understanding and Improving Fast Adversarial Training NIPS 2020
Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem CVPR 2019
Provable Robustness of ReLU networks via Maximization of Linear Regions AISTATS 2019
Provably robust boosted decision stumps and trees against adversarial attacks NIPS 2019
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation NIPS 2017