Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
Paper
•
2306.03013
•
Published
Nikola Jovanović
ni-jovanovic
AI & ML interests
Trustworthy AI, Watermarking
Recent Activity
updated
a dataset
about 2 months ago
MathArena/project_euler
updated
a dataset
3 months ago
MathArena/project_euler
published
an
article
8 months ago
Highlights from the First ICLR 2025 Watermarking Workshop
Organizations
authored
13
papers
8 months ago
BaxBench: Can LLMs Generate Correct and Secure Backends?
Paper
•
2502.11844
•
Published
Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad
Paper
•
2503.21934
•
Published
MathConstruct: Challenging LLM Reasoning with Constructive Proofs
Paper
•
2502.10197
•
Published
Towards Watermarking of Open-Source LLMs
Paper
•
2502.10525
•
Published
Ward: Provable RAG Dataset Inference via LLM Watermarks
Paper
•
2410.03537
•
Published
COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
Paper
•
2410.07959
•
Published
•
1
Discovering Clues of Spoofed LM Watermarks
Paper
•
2410.02693
•
Published
Black-Box Detection of Language Model Watermarks
Paper
•
2405.20777
•
Published
From Principle to Practice: Vertical Data Minimization for Machine Learning
Paper
•
2311.10500
•
Published
Private and Reliable Neural Network Inference
Paper
•
2210.15614
•
Published
LAMP: Extracting Text from Gradients with Language Model Priors
Paper
•
2202.08827
•
Published
Towards Sparse Hierarchical Graph Classifiers
Paper
•
1811.01287
•
Published
authored
a
paper
over 2 years ago