111 citations · 181 across the 19 of their papers we have counts for
21 papers
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…
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…
Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
Luca Beurer-Kellner, Marc Fischer, Martin Vechev
To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generatio…
Automated Classification of Model Errors on ImageNet
Momchil Peychev, Mark Niklas Müller, Marc Fischer +1
While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of…
Prompt Sketching for Large Language Models
Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer +1
Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. Ho…
Controlled Text Generation via Language Model Arithmetic
Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner +1
As Large Language Models (LLMs) are deployed more widely, customization with respect to vocabulary, style, and character becomes more important. In this work, we introduce model ar…
Understanding Certified Training with Interval Bound Propagation
Yuhao Mao, Mark Niklas Müller, Marc Fischer +1
As robustness verification methods are becoming more precise, training certifiably robust neural networks is becoming ever more relevant. To this end, certified training methods co…
TAPS: Connecting Certified and Adversarial Training
Yuhao Mao, Mark Niklas Müller, Marc Fischer +1
Training certifiably robust neural networks remains a notoriously hard problem. On one side, adversarial training optimizes under-approximations of the worst-case loss, which leads…
Efficient Certified Training and Robustness Verification of Neural ODEs
Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer +1
Neural Ordinary Differential Equations (NODEs) are a novel neural architecture, built around initial value problems with learned dynamics which are solved during inference. Thought…
Prompting Is Programming: A Query Language for Large Language Models
Luca Beurer-Kellner, Marc Fischer, Martin Vechev
Large language models have demonstrated outstanding performance on a wide range of tasks such as question answering and code generation. On a high level, given an input, a language…
Private and Reliable Neural Network Inference
Nikola Jovanović, Marc Fischer, Samuel Steffen +1
Reliable neural networks (NNs) provide important inference-time reliability guarantees such as fairness and robustness. Complementarily, privacy-preserving NN inference protects th…
Certified Training: Small Boxes are All You Need
Mark Niklas Müller, Franziska Eckert, Marc Fischer +1
To obtain, deterministic guarantees of adversarial robustness, specialized training methods are used. We propose, SABR, a novel such certified training method, based on the key ins…
(De-)Randomized Smoothing for Decision Stump Ensembles
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer +1
Tree-based models are used in many high-stakes application domains such as finance and medicine, where robustness and interpretability are of utmost importance. Yet, methods for im…
Robust and Accurate -- Compositional Architectures for Randomized Smoothing
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer +1
Randomized Smoothing (RS) is considered the state-of-the-art approach to obtain certifiably robust models for challenging tasks. However, current RS approaches drastically decrease…
Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks
Mark Niklas Müller, Marc Fischer, Robin Staab +1
We present a new abstract interpretation framework for the precise over-approximation of numerical fixpoint iterators. Our key observation is that unlike in standard abstract inter…
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…
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…
Boosting Randomized Smoothing with Variance Reduced Classifiers
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer +1
Randomized Smoothing (RS) is a promising method for obtaining robustness certificates by evaluating a base model under noise. In this work, we: (i) theoretically motivate why ensem…
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…
Learning Certified Individually Fair Representations
Anian Ruoss, Mislav Balunović, Marc Fischer +1
Fair representation learning provides an effective way of enforcing fairness constraints without compromising utility for downstream users. A desirable family of such fairness cons…
Online Robustness Training for Deep Reinforcement Learning
Marc Fischer, Matthew Mirman, Steven Stalder +1
In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which…