Search Results for author: Daniel Neider

Found 28 papers, 8 papers with code

VeriFlow: Modeling Distributions for Neural Network Verification

no code implementations20 Jun 2024 Faried Abu Zaid, Daniel Neider, Mustafa Yalçıner

Formal verification has emerged as a promising method to ensure the safety and reliability of neural networks.

Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine

no code implementations11 Feb 2024 Shayan Meshkat Alsadat, Jean-Raphael Gaglione, Daniel Neider, Ufuk Topcu, Zhe Xu

Our method uses Large Language Models (LLM) to obtain high-level domain-specific knowledge using prompt engineering instead of providing the reinforcement learning algorithm directly with the high-level knowledge which requires an expert to encode the automaton.

Language Modelling Large Language Model +2

Synthesizing Efficiently Monitorable Formulas in Metric Temporal Logic

no code implementations26 Oct 2023 Ritam Raha, Rajarshi Roy, Nathanael Fijalkow, Daniel Neider, Guillermo A. Perez

In runtime verification, manually formalizing a specification for monitoring system executions is a tedious and error-prone process.

Defending Our Privacy With Backdoors

1 code implementation12 Oct 2023 Dominik Hintersdorf, Lukas Struppek, Daniel Neider, Kristian Kersting

We propose a rather easy yet effective defense based on backdoor attacks to remove private information such as names and faces of individuals from vision-language models by fine-tuning them for only a few minutes instead of re-training them from scratch.

Interpretable Anomaly Detection via Discrete Optimization

no code implementations24 Mar 2023 Simon Lutz, Florian Wittbold, Simon Dierl, Benedikt Böing, Falk Howar, Barbara König, Emmanuel Müller, Daniel Neider

Anomaly detection is essential in many application domains, such as cyber security, law enforcement, medicine, and fraud protection.

Anomaly Detection Decision Making

Learning Temporal Logic Properties: an Overview of Two Recent Methods

no code implementations2 Dec 2022 Jean-Raphaël Gaglione, Rajarshi Roy, Nasim Baharisangari, Daniel Neider, Zhe Xu, Ufuk Topcu

Learning linear temporal logic (LTL) formulas from examples labeled as positive or negative has found applications in inferring descriptions of system behavior.

Specificity Vocal Bursts Valence Prediction

Analyzing Robustness of Angluin's L* Algorithm in Presence of Noise

no code implementations21 Sep 2022 Igor Khmelnitsky, Serge Haddad, Lina Ye, Benoît Barbot, Benedikt Bollig, Martin Leucker, Daniel Neider, Rajarshi Roy

Angluin's L* algorithm learns the minimal (complete) deterministic finite automaton (DFA) of a regular language using membership and equivalence queries.

Classification PAC learning

Learning Interpretable Temporal Properties from Positive Examples Only

1 code implementation6 Sep 2022 Rajarshi Roy, Jean-Raphaël Gaglione, Nasim Baharisangari, Daniel Neider, Zhe Xu, Ufuk Topcu

To learn meaningful models from positive examples only, we design algorithms that rely on conciseness and language minimality of models as regularizers.

Specification sketching for Linear Temporal Logic

no code implementations14 Jun 2022 Simon Lutz, Daniel Neider, Rajarshi Roy

Virtually all verification and synthesis techniques assume that the formal specifications are readily available, functionally correct, and fully match the engineer's understanding of the given system.

Neuro-Symbolic Verification of Deep Neural Networks

1 code implementation2 Mar 2022 Xuan Xie, Kristian Kersting, Daniel Neider

Formal verification has emerged as a powerful approach to ensure the safety and reliability of deep neural networks.

Adversarial Robustness Fairness

Scalable Anytime Algorithms for Learning Fragments of Linear Temporal Logic

1 code implementation13 Oct 2021 Ritam Raha, Rajarshi Roy, Nathanaël Fijalkow, Daniel Neider

Linear temporal logic (LTL) is a specification language for finite sequences (called traces) widely used in program verification, motion planning in robotics, process mining, and many other areas.

Motion Planning

Uncertainty-Aware Signal Temporal Logic Inference

1 code implementation24 May 2021 Nasim Baharisangari, Jean-Raphaël Gaglione, Daniel Neider, Ufuk Topcu, Zhe Xu

In this paper, we first investigate the uncertainties associated with trajectories of a system and represent such uncertainties in the form of interval trajectories.

Learning Linear Temporal Properties from Noisy Data: A MaxSAT Approach

no code implementations30 Apr 2021 Jean-Raphaël Gaglione, Daniel Neider, Rajarshi Roy, Ufuk Topcu, Zhe Xu

Our first algorithm infers minimal LTL formulas by reducing the inference problem to a problem in maximum satisfiability and then using off-the-shelf MaxSAT solvers to find a solution.

Parameterized Synthesis with Safety Properties

1 code implementation28 Sep 2020 Oliver Markgraf, Chih-Duo Hong, Anthony W. Lin, Muhammad Najib, Daniel Neider

Parameterized synthesis offers a solution to the problem of constructing correct and verified controllers for parameterized systems.

Logic in Computer Science Formal Languages and Automata Theory

Probably Approximately Correct Explanations of Machine Learning Models via Syntax-Guided Synthesis

no code implementations18 Sep 2020 Daniel Neider, Bishwamittra Ghosh

We propose a novel approach to understanding the decision making of complex machine learning models (e. g., deep neural networks) using a combination of probably approximately correct learning (PAC) and a logic inference methodology called syntax-guided synthesis (SyGuS).

BIG-bench Machine Learning Decision Making

Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples

no code implementations28 Jun 2020 Zhe Xu, Bo Wu, Aditya Ojha, Daniel Neider, Ufuk Topcu

We compare our algorithm with the state-of-the-art RL algorithms for non-Markovian reward functions, such as Joint Inference of Reward machines and Policies for RL (JIRP), Learning Reward Machine (LRM), and Proximal Policy Optimization (PPO2).

Active Learning Q-Learning +2

A Formal Language Approach to Explaining RNNs

no code implementations12 Jun 2020 Bishwamittra Ghosh, Daniel Neider

This paper presents LEXR, a framework for explaining the decision making of recurrent neural networks (RNNs) using a formal description language called Linear Temporal Logic (LTL).

Decision Making Descriptive

Learning Interpretable Models in the Property Specification Language

no code implementations10 Feb 2020 Rajarshi Roy, Dana Fisman, Daniel Neider

In contrast to most of the recent work in this area, which focuses on descriptions expressed in Linear Temporal Logic (LTL), we develop a learning algorithm for formulas in the IEEE standard temporal logic PSL (Property Specification Language).

Joint Inference of Reward Machines and Policies for Reinforcement Learning

no code implementations12 Sep 2019 Zhe Xu, Ivan Gavran, Yousef Ahmad, Rupak Majumdar, Daniel Neider, Ufuk Topcu, Bo Wu

The experiments show that learning high-level knowledge in the form of reward machines can lead to fast convergence to optimal policies in RL, while standard RL methods such as q-learning and hierarchical RL methods fail to converge to optimal policies after a substantial number of training steps in many tasks.

Q-Learning reinforcement-learning +1

Learning-Based Synthesis of Safety Controllers

no code implementations21 Jan 2019 Daniel Neider, Oliver Markgraf

We propose a machine learning framework to synthesize reactive controllers for systems whose interactions with their adversarial environment are modeled by infinite-duration, two-player games over (potentially) infinite graphs.

Motion Planning

Horn-ICE Learning for Synthesizing Invariants and Contracts

no code implementations26 Dec 2017 Deepak D'Souza, P. Ezudheen, Pranav Garg, P. Madhusudan, Daniel Neider

We design learning algorithms for synthesizing invariants using Horn implication counterexamples (Horn-ICE), extending the ICE-learning model.

Invariant Synthesis for Incomplete Verification Engines

no code implementations15 Dec 2017 Daniel Neider, Pranav Garg, P. Madhusudan, Shambwaditya Saha, Daejun Park

We propose a framework for synthesizing inductive invariants for incomplete verification engines, which soundly reduce logical problems in undecidable theories to decidable theories.

An Automaton Learning Approach to Solving Safety Games over Infinite Graphs

no code implementations7 Jan 2016 Daniel Neider, Ufuk Topcu

We propose a method to construct finite-state reactive controllers for systems whose interactions with their adversarial environment are modeled by infinite-duration two-player games over (possibly) infinite graphs.

Motion Planning

Robust Linear Temporal Logic

1 code implementation30 Oct 2015 Paulo Tabuada, Daniel Neider

Although it is widely accepted that every system should be robust, in the sense that "small" violations of environment assumptions should lead to "small" violations of system guarantees, it is less clear how to make this intuitive notion of robustness mathematically precise.

Logic in Computer Science Systems and Control Optimization and Control 03B44 F.4.1

Cannot find the paper you are looking for? You can Submit a new open access paper.