21 citations · 54 across the 18 of their papers we have counts for
18 papers
Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
Ivo Petrov, Jasper Dekoninck, Dimitar I. Dimitrov +1
Large language models (LLMs) have become capable mathematical problem-solvers, often producing correct proofs for challenging problems. However, correctness alone is not sufficient…
TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization
William Kalikman, Ivo Petrov, Dimitar I. Dimitrov +1
Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local. However, prior gradient i…
SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics
Nikolay Georgiev, Maria Drencheva, Kseniia Ibragimova +3
As agentic AI systems tackle more complex mathematical tasks, they increasingly rely on information retrieval (IR) to search problem databases, theorem libraries, and educational r…
SPEAR++: Scaling Gradient Inversion via Sparsely-Used Dictionary Learning
Alexander Bakarsky, Dimitar I. Dimitrov, Maximilian Baader +1
Federated Learning has seen an increased deployment in real-world scenarios recently, as it enables the distributed training of machine learning models without explicit data sharin…
LARP: Learner-Agnostic Robust Data Prefiltering
Kristian Minchev, Dimitar I. Dimitrov, Nikola Konstantinov
Public datasets, crucial for modern machine learning and statistical inference, often contain low-quality or contaminated samples that can harm model performance. This creates a ne…
MixAT: Combining Continuous and Discrete Adversarial Training for LLMs
Csaba Dékány, Stefan Balauca, Robin Staab +2
Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although a…
GRAIN: Exact Graph Reconstruction from Gradients
Maria Drencheva, Ivo Petrov, Maximilian Baader +2
Federated learning claims to enable collaborative model training among multiple clients with data privacy by transmitting gradient updates instead of the actual client data. Howeve…
BgGPT 1.0: Extending English-centric LLMs to other languages
Anton Alexandrov, Veselin Raychev, Dimitar I. Dimitrov +3
We present BgGPT-Gemma-2-27B-Instruct and BgGPT-Gemma-2-9B-Instruct: continually pretrained and fine-tuned versions of Google's Gemma-2 models, specifically optimized for Bulgarian…
Modular Synthesis of Efficient Quantum Uncomputation
Hristo Venev, Timon Gehr, Dimitar Dimitrov +1
A key challenge of quantum programming is uncomputation: the reversible deallocation of qubits. And while there has been much recent progress on automating uncomputation, state-of-…
SPEAR:Exact Gradient Inversion of Batches in Federated Learning
Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller +1
Federated learning is a framework for collaborative machine learning where clients only share gradient updates and not their private data with a server. However, it was recently sh…
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanović +1
Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. H…
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…
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…
Shared Certificates for Neural Network Verification
Marc Fischer, Christian Sprecher, Dimitar I. Dimitrov +2
Existing neural network verifiers compute a proof that each input is handled correctly under a given perturbation by propagating a symbolic abstraction of reachable values at each…
Provably Robust Adversarial Examples
Dimitar I. Dimitrov, Gagandeep Singh, Timon Gehr +1
We introduce the concept of provably robust adversarial examples for deep neural networks - connected input regions constructed from standard adversarial examples which are guarant…