Mislav Balunovic

48 papers A* 20Journal 25Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Language Models are Advanced Anonymizers. ICLR Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev
2025	J	`jnl`	MathArena: Evaluating LLMs on Uncontaminated Math Competitions. CoRR Mislav Balunovic, Jasper Dekoninck, Ivo Petrov, Nikola Jovanovic, Martin T. Vechev
2025	A*	`conf`	MathConstruct: Challenging LLM Reasoning with Constructive Proofs. ICML Mislav Balunovic, Jasper Dekoninck, Nikola Jovanovic, Ivo Petrov, Martin T. Vechev
2025	J	`jnl`	MathConstruct: Challenging LLM Reasoning with Constructive Proofs. CoRR Mislav Balunovic, Jasper Dekoninck, Nikola Jovanovic, Ivo Petrov, Martin T. Vechev
2025	J	`jnl`	Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad. CoRR Ivo Petrov, Jasper Dekoninck, Lyuben Baltadzhiev, Maria Drencheva, Kristian Minchev, Mislav Balunovic, Nikola Jovanovic, Martin T. Vechev
2025	J	`jnl`	The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical Proofs. CoRR Jasper Dekoninck, Ivo Petrov, Kristian Minchev, Mislav Balunovic, Martin T. Vechev, Miroslav Marinov, Maria Drencheva, Lyuba Konova, Milen Shumanov, Kaloyan Tsvetkov, Nikolay Drenchev, Lazar Todorov, Kalina Nikolova, Nikolay Georgiev, Vanesa Kalinkova, Margulan Ismoldayev
2025	J	`jnl`	ToolFuzz - Automated Agent Tool Testing. CoRR Ivan Milev, Mislav Balunovic, Maximilian Baader, Martin T. Vechev
2024	J	`jnl`	AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents. CoRR Edoardo Debenedetti, Jie Zhang, Mislav Balunovic, Luca Beurer-Kellner, Marc Fischer, Florian Tramèr
2024	A*	`conf`	AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. NeurIPS Edoardo Debenedetti, Jie Zhang, Mislav Balunovic, Luca Beurer-Kellner, Marc Fischer, Florian Tramèr
2024	A*	`conf`	Beyond Memorization: Violating Privacy via Inference with Large Language Models. ICLR Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev
2024	J	`jnl`	COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act. CoRR Philipp Guldimann, Alexander Spiridonov, Robin Staab, Nikola Jovanovic, Mark Vero, Velko Vechev, Anna Gueorguieva, Mislav Balunovic, Nikola Konstantinov, Pavol Bielik, Petar Tsankov, Martin T. Vechev
2024	A*	`conf`	CuTS: Customizable Tabular Synthetic Data Generation. ICML Mark Vero, Mislav Balunovic, Martin T. Vechev
2024	—	`—`	Formal and Statistical Certification of Robustness and Fairness for AI. Mislav Balunovic
2024	A*	`conf`	From Principle to Practice: Vertical Data Minimization for Machine Learning. SP Robin Staab, Nikola Jovanovic, Mislav Balunovic, Martin T. Vechev
2024	J	`jnl`	Large Language Models are Advanced Anonymizers. CoRR Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev
2023	J	`jnl`	Beyond Memorization: Violating Privacy Via Inference with Large Language Models. CoRR Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev
2023	A*	`conf`	FARE: Provably Fair Representation Learning with Practical Certificates. ICML Nikola Jovanovic, Mislav Balunovic, Dimitar Iliev Dimitrov, Martin T. Vechev
2023	J	`jnl`	From Principle to Practice: Vertical Data Minimization for Machine Learning. CoRR Robin Staab, Nikola Jovanovic, Mislav Balunovic, Martin T. Vechev
2023	J	`jnl`	Programmable Synthetic Tabular Data Generation. CoRR Mark Vero, Mislav Balunovic, Martin T. Vechev
2023	A*	`conf`	TabLeak: Tabular Data Leakage in Federated Learning. ICML Mark Vero, Mislav Balunovic, Dimitar Iliev Dimitrov, Martin T. Vechev
2022	A*	`conf`	Bayesian Framework for Gradient Leakage. ICLR Mislav Balunovic, Dimitar Iliev Dimitrov, Robin Staab, Martin T. Vechev
2022	J	`jnl`	Data Leakage in Federated Averaging. CoRR Dimitar I. Dimitrov, Mislav Balunovic, Nikola Konstantinov, Martin T. Vechev
2022	J	`jnl`	Data Leakage in Federated Averaging. Trans. Mach. Learn. Res. Dimitar Iliev Dimitrov, Mislav Balunovic, Nikola Konstantinov, Martin T. Vechev
2022	J	`jnl`	Data Leakage in Tabular Federated Learning. CoRR Mark Vero, Mislav Balunovic, Dimitar I. Dimitrov, Martin T. Vechev
2022	J	`jnl`	FARE: Provably Fair Representation Learning. CoRR Nikola Jovanovic, Mislav Balunovic, Dimitar I. Dimitrov, Martin T. Vechev
2022	A*	`conf`	Fair Normalizing Flows. ICLR Mislav Balunovic, Anian Ruoss, Martin T. Vechev
2022	A*	`conf`	LAMP: Extracting Text from Gradients with Language Model Priors. NeurIPS Mislav Balunovic, Dimitar I. Dimitrov, Nikola Jovanovic, Martin T. Vechev
2022	J	`jnl`	LAMP: Extracting Text from Gradients with Language Model Priors. CoRR Dimitar I. Dimitrov, Mislav Balunovic, Nikola Jovanovic, Martin T. Vechev
2022	—	`conf`	Latent Space Smoothing for Individually Fair Representations. ECCV (13) Momchil Peychev, Anian Ruoss, Mislav Balunovic, Maximilian Baader, Martin T. Vechev
2022	J	`jnl`	On the Paradox of Certified Training. Trans. Mach. Learn. Res. Nikola Jovanovic, Mislav Balunovic, Maximilian Baader, Martin T. Vechev
2021	J	`jnl`	Bayesian Framework for Gradient Leakage. CoRR Mislav Balunovic, Dimitar I. Dimitrov, Robin Staab, Martin T. Vechev
2021	J	`jnl`	Certified Defenses: Why Tighter Relaxations May Hurt Training? CoRR Nikola Jovanovic, Mislav Balunovic, Maximilian Baader, Martin T. Vechev
2021	A*	`conf`	Certify or Predict: Boosting Certified Robustness with Compositional Architectures. ICLR Mark Niklas Müller, Mislav Balunovic, Martin T. Vechev
2021	A*	`conf`	Efficient Certification of Spatial Robustness. AAAI Anian Ruoss, Maximilian Baader, Mislav Balunovic, Martin T. Vechev
2021	J	`jnl`	Fair Normalizing Flows. CoRR Mislav Balunovic, Anian Ruoss, Martin T. Vechev
2021	J	`jnl`	Latent Space Smoothing for Individually Fair Representations. CoRR Momchil Peychev, Anian Ruoss, Mislav Balunovic, Maximilian Baader, Martin T. Vechev
2021	A*	`conf`	Robustness Certification for Point Cloud Models. ICCV Tobias Lorenz, Anian Ruoss, Mislav Balunovic, Gagandeep Singh, Martin T. Vechev
2021	J	`jnl`	Robustness Certification for Point Cloud Models. CoRR Tobias Lorenz, Anian Ruoss, Mislav Balunovic, Gagandeep Singh, Martin T. Vechev
2021	—	`conf`	Scalable Polyhedral Verification of Recurrent Neural Networks. CAV (1) Wonryong Ryou, Jiayu Chen, Mislav Balunovic, Gagandeep Singh, Andrei Marian Dan, Martin T. Vechev
2020	A*	`conf`	Adversarial Training and Provable Defenses: Bridging the Gap. ICLR Mislav Balunovic, Martin T. Vechev
2020	J	`jnl`	Efficient Certification of Spatial Robustness. CoRR Anian Ruoss, Maximilian Baader, Mislav Balunovic, Martin T. Vechev
2020	J	`jnl`	Fast and Effective Robustness Certification for Recurrent Neural Networks. CoRR Wonryong Ryou, Jiayu Chen, Mislav Balunovic, Gagandeep Singh, Andrei Marian Dan, Martin T. Vechev
2020	A*	`conf`	Learning Certified Individually Fair Representations. NeurIPS Anian Ruoss, Mislav Balunovic, Marc Fischer, Martin T. Vechev
2020	J	`jnl`	Learning Certified Individually Fair Representations. CoRR Anian Ruoss, Mislav Balunovic, Marc Fischer, Martin T. Vechev
2019	A*	`conf`	Certifying Geometric Robustness of Neural Networks. NeurIPS Mislav Balunovic, Maximilian Baader, Gagandeep Singh, Timon Gehr, Martin T. Vechev
2019	A*	`conf`	DL2: Training and Querying Neural Networks with Logic. ICML Marc Fischer, Mislav Balunovic, Dana Drachsler-Cohen, Timon Gehr, Ce Zhang, Martin T. Vechev
2019	A*	`conf`	Learning to Fuzz from Symbolic Execution with Application to Smart Contracts. CCS Jingxuan He, Mislav Balunovic, Nodar Ambroladze, Petar Tsankov, Martin T. Vechev
2018	A*	`conf`	Learning to Solve SMT Formulas. NeurIPS Mislav Balunovic, Pavol Bielik, Martin T. Vechev