Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from EDBT 2026 / reviewers in the wild / expert

Niklas Risse

dblp:263/6877 · DBLP profile ↗
← Back
4ranked-venue papers
3as first author
4since 2021 · last 2026
0000-0002-0666-5025ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Security and privacy · 2 · 1 first-author · 2 since 2021Artificial intelligence and machine learning · 1 · 1 first-author · 1 since 2021Software engineering, systems software and programming languages · 1 · 1 first-author · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Network and information security
3 papers
Blockchain and cryptocurrency security · 46% Security and privacy of machine learning · 32% Systems and software security · 21%
Software engineering, system software, and programming languages
1 paper
Empirical software engineering · 100%
Artificial intelligence
2 papers
Language models and text generation · 57% Deep learning architectures and training · 43%

Topics — the 3 heaviest of 6, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Blockchain and cryptocurrency security › smart contract security
vulnerability detection		 1.422024
Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection · USENIX Security Symposium 2024
Detecting Overfitting of Machine Learning Techniques for Automatic Vulnerability Detection · ESEC/SIGSOFT FSE 2023
Systems and software security › vulnerability discovery
machine-learning-based vulnerability detection		 0.712023
Detecting Overfitting of Machine Learning Techniques for Automatic Vulnerability Detection · ESEC/SIGSOFT FSE 2023
Empirical software engineering
mining software repositories		 0.712023
Detecting Overfitting of Machine Learning Techniques for Automatic Vulnerability Detection · ESEC/SIGSOFT FSE 2023

Methods — techniques the papers use, named apart from their topics

machine learning · 2.8LLM security analysis · 2.0
YearPublicationVenuePosition
2026 Chasing Shadows: Pitfalls in LLM Security Research
Jonathan Evertz, Niklas Risse, Nicolai Neuer, Andreas Müller 0025, Philipp Normann, Gaetano Sapia, Srishti Gupta 0004, Soumya Shaw, Devansh Srivastav, Christian Wressnegger, Erwin Quiring, Thorsten Eisenhofer, Daniel Arp, Lea Schönherr
 NDSS2
2024 Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection
Niklas Risse, Marcel Böhme
 USENIX Security Symposium1
2023 Detecting Overfitting of Machine Learning Techniques for Automatic Vulnerability Detection
abstract
Recent results of machine learning for automatic vulnerability detection have been very promising indeed: Given only the source code of a function f, models trained by machine learning techniques can decide if f contains a security flaw with up to 70% accuracy.
Niklas Risse
 ESEC/SIGSOFT FSE1
2021 How to Compare Adversarial Robustness of Classifiers from a Global Perspective
Niklas Risse, Christina Göpfert, Jan Philip Göpfert
 ICANN (1)1