no code implementations • 11 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.
no code implementations • 26 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.
1 code implementation • 12 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.
no code implementations • 23 Jun 2023 • Yash Paliwal, Rajarshi Roy, Jean-Raphaël Gaglione, Nasim Baharisangari, Daniel Neider, Xiaoming Duan, Ufuk Topcu, Zhe Xu
We study a class of reinforcement learning (RL) tasks where the objective of the agent is to accomplish temporally extended goals.
no code implementations • 24 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.
no code implementations • 10 Mar 2023 • Fabian Hartung, Billy Joe Franks, Tobias Michels, Dennis Wagner, Philipp Liznerski, Steffen Reithermann, Sophie Fellenz, Fabian Jirasek, Maja Rudolph, Daniel Neider, Heike Leitte, Chen Song, Benjamin Kloepper, Stephan Mandt, Michael Bortz, Jakob Burger, Hans Hasse, Marius Kloft
Our extensive study will facilitate choosing appropriate anomaly detection methods in industrial applications.
no code implementations • 2 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.
no code implementations • 21 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.
1 code implementation • 6 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.
no code implementations • 14 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.
1 code implementation • 2 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.
1 code implementation • 12 Nov 2021 • Lukas Struppek, Dominik Hintersdorf, Daniel Neider, Kristian Kersting
Specifically, we show that current deep perceptual hashing may not be robust.
1 code implementation • 13 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.
1 code implementation • 24 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.
no code implementations • 30 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.
1 code implementation • 28 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
no code implementations • 22 Sep 2020 • Igor Khmelnitsky, Daniel Neider, Rajarshi Roy, Benoît Barbot, Benedikt Bollig, Alain Finkel, Serge Haddad, Martin Leucker, Lina Ye
This paper presents a property-directed approach to verifying recurrent neural networks (RNNs).
no code implementations • 18 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).
no code implementations • 28 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).
no code implementations • 12 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).
no code implementations • 10 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).
no code implementations • 12 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.
no code implementations • 21 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.
no code implementations • 26 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.
no code implementations • 15 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.
no code implementations • 7 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.
1 code implementation • 30 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