38 citations · 111 across the 13 of their papers we have counts for
15 papers
MathArena: Evaluating LLMs on Uncontaminated Math Competitions
Mislav Balunović, Jasper Dekoninck, Ivo Petrov +2
The rapid advancement of reasoning capabilities in large language models (LLMs) has led to notable improvements on mathematical benchmarks. However, many of the most commonly used…
ToolFuzz -- Automated Agent Tool Testing
Ivan Milev, Mislav Balunović, Maximilian Baader +1
Large Language Model (LLM) Agents leverage the advanced reasoning capabilities of LLMs in real-world applications. To interface with an environment, these agents often rely on tool…
Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad
Ivo Petrov, Jasper Dekoninck, Lyuben Baltadzhiev +5
Recent math benchmarks for large language models (LLMs) such as MathArena indicate that state-of-the-art reasoning models achieve impressive performance on mathematical competition…
MathConstruct: Challenging LLM Reasoning with Constructive Proofs
Mislav Balunović, Jasper Dekoninck, Nikola Jovanović +2
While Large Language Models (LLMs) demonstrate impressive performance in mathematics, existing math benchmarks come with significant limitations. Many focus on problems with fixed…
COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
Philipp Guldimann, Alexander Spiridonov, Robin Staab +9
The EU's Artificial Intelligence Act (AI Act) is a significant step towards responsible AI development, but lacks clear technical interpretation, making it difficult to assess mode…
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
Edoardo Debenedetti, Jie Zhang, Mislav Balunović +3
AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data retu…
Large Language Models are Advanced Anonymizers
Robin Staab, Mark Vero, Mislav Balunović +1
Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing…
Beyond Memorization: Violating Privacy Via Inference with Large Language Models
Robin Staab, Mark Vero, Mislav Balunović +1
Current privacy research on large language models (LLMs) primarily focuses on the issue of extracting memorized training data. At the same time, models' inference capabilities have…
CuTS: Customizable Tabular Synthetic Data Generation
Mark Vero, Mislav Balunović, Martin Vechev
Privacy, data quality, and data sharing concerns pose a key limitation for tabular data applications. While generating synthetic data resembling the original distribution addresses…
FARE: Provably Fair Representation Learning with Practical Certificates
Nikola Jovanović, Mislav Balunović, Dimitar I. Dimitrov +1
Fair representation learning (FRL) is a popular class of methods aiming to produce fair classifiers via data preprocessing. Recent regulatory directives stress the need for FRL met…
TabLeak: Tabular Data Leakage in Federated Learning
Mark Vero, Mislav Balunović, Dimitar I. Dimitrov +1
While federated learning (FL) promises to preserve privacy, recent works in the image and text domains have shown that training updates leak private client data. However, most high…
Data Leakage in Federated Averaging
Dimitar I. Dimitrov, Mislav Balunović, Nikola Konstantinov +1
Recent attacks have shown that user data can be recovered from FedSGD updates, thus breaking privacy. However, these attacks are of limited practical relevance as federated learnin…
LAMP: Extracting Text from Gradients with Language Model Priors
Mislav Balunović, Dimitar I. Dimitrov, Nikola Jovanović +1
Recent work shows that sensitive user data can be reconstructed from gradient updates, breaking the key privacy promise of federated learning. While success was demonstrated primar…
Latent Space Smoothing for Individually Fair Representations
Momchil Peychev, Anian Ruoss, Mislav Balunović +2
Fair representation learning transforms user data into a representation that ensures fairness and utility regardless of the downstream application. However, learning individually f…
Bayesian Framework for Gradient Leakage
Mislav Balunović, Dimitar I. Dimitrov, Robin Staab +1
Federated learning is an established method for training machine learning models without sharing training data. However, recent work has shown that it cannot guarantee data privacy…