-
EPFL
- Lausanne
- https://andriushchenko.me/
- @maksym_andr
Highlights
- Pro
Block or Report
Block or report max-andr
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
tml-epfl/llm-adaptive-attacks
tml-epfl/llm-adaptive-attacks PublicJailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]
-
JailbreakBench/jailbreakbench
JailbreakBench/jailbreakbench PublicAn Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]
-
RobustBench/robustbench
RobustBench/robustbench PublicRobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]
-
tml-epfl/understanding-fast-adv-training
tml-epfl/understanding-fast-adv-training PublicUnderstanding and Improving Fast Adversarial Training [NeurIPS 2020]
-
square-attack
square-attack PublicSquare Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]
-
relu_networks_overconfident
relu_networks_overconfident PublicWhy ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [CVPR 2019, oral]
If the problem persists, check the GitHub status page or contact support.