Picture for Nikola Jovanović

Nikola Jovanović

COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act

Add code
Oct 10, 2024
Figure 1 for COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
Figure 2 for COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
Figure 3 for COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
Figure 4 for COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
Viaarxiv icon

Ward: Provable RAG Dataset Inference via LLM Watermarks

Add code
Oct 04, 2024
Viaarxiv icon

Discovering Clues of Spoofed LM Watermarks

Add code
Oct 03, 2024
Figure 1 for Discovering Clues of Spoofed LM Watermarks
Figure 2 for Discovering Clues of Spoofed LM Watermarks
Figure 3 for Discovering Clues of Spoofed LM Watermarks
Figure 4 for Discovering Clues of Spoofed LM Watermarks
Viaarxiv icon

Back to the Drawing Board for Fair Representation Learning

Add code
May 28, 2024
Viaarxiv icon

Watermark Stealing in Large Language Models

Add code
Feb 29, 2024
Figure 1 for Watermark Stealing in Large Language Models
Figure 2 for Watermark Stealing in Large Language Models
Figure 3 for Watermark Stealing in Large Language Models
Figure 4 for Watermark Stealing in Large Language Models
Viaarxiv icon

From Principle to Practice: Vertical Data Minimization for Machine Learning

Add code
Nov 22, 2023
Figure 1 for From Principle to Practice: Vertical Data Minimization for Machine Learning
Figure 2 for From Principle to Practice: Vertical Data Minimization for Machine Learning
Figure 3 for From Principle to Practice: Vertical Data Minimization for Machine Learning
Figure 4 for From Principle to Practice: Vertical Data Minimization for Machine Learning
Viaarxiv icon

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning

Add code
Jun 16, 2023
Viaarxiv icon

Private and Reliable Neural Network Inference

Add code
Oct 27, 2022
Viaarxiv icon

FARE: Provably Fair Representation Learning

Add code
Oct 13, 2022
Figure 1 for FARE: Provably Fair Representation Learning
Figure 2 for FARE: Provably Fair Representation Learning
Figure 3 for FARE: Provably Fair Representation Learning
Figure 4 for FARE: Provably Fair Representation Learning
Viaarxiv icon

LAMP: Extracting Text from Gradients with Language Model Priors

Add code
Feb 17, 2022
Figure 1 for LAMP: Extracting Text from Gradients with Language Model Priors
Figure 2 for LAMP: Extracting Text from Gradients with Language Model Priors
Figure 3 for LAMP: Extracting Text from Gradients with Language Model Priors
Figure 4 for LAMP: Extracting Text from Gradients with Language Model Priors
Viaarxiv icon