Daniel Neider
YOU?
Author Swipe
Let’s Talk AI with Computer Science Expert Daniel Neider Open
AI will increasingly impact our future. Let’s work together to make it safe and bright. My personal AI mission: To advance the field of artificial intelligence (AI) by developing novel machine learning techniques and formal methods that en…
On Uniformly Scaling Flows: A Density-Aligned Approach to Deep One-Class Classification Open
Unsupervised anomaly detection is often framed around two widely studied paradigms. Deep one-class classification, exemplified by Deep SVDD, learns compact latent representations of normality, while density estimators realized by normalizi…
Formal verification for robo-advisors: Irrelevant for subjective end-user trust, yet decisive for investment behavior? Open
This online-vignette study investigates the impact of certification and verification as measures for quality assurance of AI on trust and use of a robo-advisor. Confronting 520 participants with an imaginary situation where they were using…
Fine-Tuning Multilingual Language Models for Code Review: An Empirical Study on Industrial C# Projects Open
Code review is essential for maintaining software quality but often time-consuming and cognitively demanding, especially in industrial environments. Recent advancements in language models (LMs) have opened new avenues for automating core r…
Temporal Conjunctive Query Answering via Rewriting Open
Querying temporal data has recently gained traction in several artificial intelligence applications. As operational domains of intelligent agents are constantly being expanded, there is a strong need for representing domain knowledge. This…
A framework for computing upper bounds in passive learning settings Open
The task of inferring logical formulas from examples has garnered significant attention as a means to assist engineers in creating formal specifications used in the design, synthesis, and verification of computing systems. Among various ap…
What is Formal Verification without Specifications? A Survey on mining LTL Specifications Open
Virtually all verification techniques using formal methods rely on the availability of a formal specification, which describes the design requirements precisely. However, formulating specifications remains a manual task that is notoriously…
Accessible Smart Contracts Verification: Synthesizing Formal Models with Tamed LLMs Open
When blockchain systems are said to be trustless, what this really means is that all the trust is put into software. Thus, there are strong incentives to ensure blockchain software is correct -- vulnerabilities here cost millions and break…
Logic and Neural Networks (Dagstuhl Seminar 25061) Open
Logic and learning are central to Computer Science, and in particular to AI-related research. Already Alan Turing envisioned in his 1950 "Computing Machinery and Intelligence" paper a combination of statistical (ab initio) machine learning…
Learning Tree Pattern Transformations Open
Explaining why and how a tree t structurally differs from another tree t^⋆ is a question that is encountered throughout computer science, including in understanding tree-structured data such as XML or JSON data. In this article, we explore…
The Complexity of Learning LTL, CTL and ATL Formulas Open
We consider the problem of learning temporal logic formulas from examples of system behavior. Learning temporal properties has crystallized as an effective means to explain complex temporal behaviors. Several efficient algorithms have been…
Defending Our Privacy with Backdoors Open
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy atta…
Learning Branching-Time Properties in CTL and ATL via Constraint Solving Open
We address the problem of learning temporal properties from the branching-time behavior of systems. Existing research in this field has mostly focused on learning linear temporal properties specified using popular logics, such as Linear Te…
Learning Branching-Time Properties in CTL and ATL via Constraint Solving Open
We address the problem of learning temporal properties from the branching-time behavior of systems. Existing research in this field has mostly focused on learning linear temporal properties specified using popular logics, such as Linear Te…
VeriFlow: Modeling Distributions for Neural Network Verification Open
Formal verification has emerged as a promising method to ensure the safety and reliability of neural networks. However, many relevant properties, such as fairness or global robustness, pertain to the entire input space. If one applies veri…
Robust computation tree logic Open
It is widely accepted that every system should be robust in that “small” violations of environment assumptions should lead to “small” violations of system guarantees, but it is less clear how to make this intuition mathematically precise. …
Analyzing Robustness of Angluin's L$^*$ Algorithm in Presence of Noise Open
Angluin's L$^*$ algorithm learns the minimal deterministic finite automaton (DFA) of a regular language using membership and equivalence queries. Its probabilistic approximatively correct (PAC) version substitutes an equivalence query by n…
Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine Open
We present LARL-RM (Large language model-generated Automaton for Reinforcement Learning with Reward Machine) algorithm in order to encode high-level knowledge into reinforcement learning using automaton to expedite the reinforcement learni…
Scarlet: Scalable Anytime Algorithms for LearningFragments of Linear Temporal Logic Open
In the past decade, incorporating data-driven AI techniques in system design has become mainstream in almost all branches of science and technology.Typically, systems powered by AI tend to be rather complex, far beyond human understanding.…
Learning Temporal Properties is NP-hard Open
We investigate the complexity of LTL learning, which consists in deciding given a finite set of positive ultimately periodic words, a finite set of negative ultimately periodic words, and a bound B given in unary, if there is an LTL-formul…
Synthesizing Efficiently Monitorable Formulas in Metric Temporal Logic Open
In runtime verification, manually formalizing a specification for monitoring system executions is a tedious and error-prone process. To address this issue, we consider the problem of automatically synthesizing formal specifications from sy…
Inferring Properties in Computation Tree Logic Open
We consider the problem of automatically inferring specifications in the branching-time logic, Computation Tree Logic (CTL), from a given system. Designing functional and usable specifications has always been one of the biggest challenges …
Defending Our Privacy With Backdoors Open
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy atta…
Robust Alternating-Time Temporal Logic Open
In multi-agent system design, a crucial aspect is to ensure robustness, meaning that for a coalition of agents A, small violations of adversarial assumptions only lead to small violations of A's goals. In this paper we introduce a logical …
Learning Interpretable Temporal Properties from Positive Examples Only Open
We consider the problem of explaining the temporal behavior of black-box systems using human-interpretable models. Following recent research trends, we rely on the fundamental yet interpretable models of deterministic finite automata (DFAs…
View article: Reinforcement Learning with Temporal-Logic-Based Causal Diagrams
Reinforcement Learning with Temporal-Logic-Based Causal Diagrams Open
We study a class of reinforcement learning (RL) tasks where the objective of the agent is to accomplish temporally extended goals. In this setting, a common approach is to represent the tasks as deterministic finite automata (DFA) and inte…
Analyzing Robustness of Angluin's L$^*$ Algorithm in Presence of Noise Open
Angluin's L$^*$ algorithm learns the minimal deterministic finite automaton (DFA) of a regular language using membership and equivalence queries. Its probabilistic approximatively correct (PAC) version substitutes an equivalence query by n…