8 citations · 27 across the 23 of their papers we have counts for
24 papers
AutoBaxBuilder: Bootstrapping Code Security Benchmarking
Tobias von Arx, Niels Mündler, Mark Vero +2
As large language models (LLMs) see wide adoption in software engineering, the reliable assessment of the correctness and security of LLM-generated code is crucial. Notably, prior…
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…
CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization
Debeshee Das, Luca Beurer-Kellner, Marc Fischer +1
The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-de…
Adaptive Generation of Bias-Eliciting Questions for LLMs
Robin Staab, Jasper Dekoninck, Maximilian Baader +1
Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions of users worldwide. Despite their widespread adoption, growing relia…
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…
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…
BaxBench: Can LLMs Generate Correct and Secure Backends?
Mark Vero, Niels Mündler, Victor Chibotaru +5
Automatic program generation has long been a fundamental challenge in computer science. Recent benchmarks have shown that large language models (LLMs) can effectively generate code…
A Unified Approach to Routing and Cascading for LLMs
Jasper Dekoninck, Maximilian Baader, Martin Vechev
The availability of a wide range of large language models (LLMs) embedded in various agentic systems has significantly increased the potential of model selection strategies to impr…
Ward: Provable RAG Dataset Inference via LLM Watermarks
Nikola Jovanović, Robin Staab, Maximilian Baader +1
RAG enables LLMs to easily incorporate external data, raising concerns for data owners regarding unauthorized usage of their content. The challenge of detecting such unauthorized u…
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
Jasper Dekoninck, Maximilian Baader, Martin Vechev
Rating-based human evaluation has become an essential tool to accurately evaluate the impressive performance of large language models (LLMs). However, current rating systems suffer…
Certified Robustness to Data Poisoning in Gradient-Based Training
Philip Sosnin, Mark N. Müller, Maximilian Baader +2
Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. P…
DAGER: Exact Gradient Inversion for Large Language Models
Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader +2
Federated learning works by aggregating locally computed gradients from multiple clients, thus enabling collaborative training without sharing private client data. However, prior w…
Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations
Stefan Balauca, Mark Niklas Müller, Yuhao Mao +3
Training neural networks with high certified accuracy against adversarial examples remains an open challenge despite significant efforts. While certification methods can effectivel…
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…
Evading Data Contamination Detection for Language Models is (too) Easy
Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader +2
Large language models are widespread, with their performance on benchmarks frequently guiding user preferences for one model over another. However, the vast amount of data these mo…
Expressivity of ReLU-Networks under Convex Relaxations
Maximilian Baader, Mark Niklas Müller, Yuhao Mao +1
Convex relaxations are a key component of training and certifying provably safe neural networks. However, despite substantial progress, a wide and poorly understood accuracy gap to…
Abstraqt: Analysis of Quantum Circuits via Abstract Stabilizer Simulation
Benjamin Bichsel, Anouk Paradis, Maximilian Baader +1
Stabilizer simulation can efficiently simulate an important class of quantum circuits consisting exclusively of Clifford gates. However, all existing extensions of this simulation…
The Fundamental Limits of Interval Arithmetic for Neural Networks
Matthew Mirman, Maximilian Baader, Martin Vechev
Interval analysis (or interval bound propagation, IBP) is a popular technique for verifying and training provably robust deep neural networks, a fundamental challenge in the area o…
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…
Scalable Certified Segmentation via Randomized Smoothing
Marc Fischer, Maximilian Baader, Martin Vechev
We present a new certification method for image and point cloud segmentation based on randomized smoothing. The method leverages a novel scalable algorithm for prediction and certi…
On the Paradox of Certified Training
Nikola Jovanović, Mislav Balunović, Maximilian Baader +1
Certified defenses based on convex relaxations are an established technique for training provably robust models. The key component is the choice of relaxation, varying from simple…
Efficient Certification of Spatial Robustness
Anian Ruoss, Maximilian Baader, Mislav Balunović +1
Recent work has exposed the vulnerability of computer vision models to vector field attacks. Due to the widespread usage of such models in safety-critical applications, it is cruci…
Certified Defense to Image Transformations via Randomized Smoothing
Marc Fischer, Maximilian Baader, Martin Vechev
We extend randomized smoothing to cover parameterized transformations (e.g., rotations, translations) and certify robustness in the parameter space (e.g., rotation angle). This is…
Universal Approximation with Certified Networks
Maximilian Baader, Matthew Mirman, Martin Vechev
Training neural networks to be certifiably robust is critical to ensure their safety against adversarial attacks. However, it is currently very difficult to train a neural network…