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

Behrad Tajalli

dblp:339/7061 · DBLP profile ↗
← Back
2ranked-venue papers
2as first author
2since 2021 · last 2026
0009-0001-0636-3385ORCID · reported

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

Security and privacy · 2 · 2 first-author · 2 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
2 papers
Security and privacy of machine learning · 100%
Databases, data mining, and information retrieval
1 paper
Data mining · 100%
Artificial intelligence
1 paper
Deep learning architectures and training · 100%

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

TopicWeightPapersLastEvidence papers
Security and privacy of machine learning › adversarial attack
backdoor attack		 1.722026
CatBack: Universal Backdoor Attacks on Tabular Data via Categorical Encoding · NDSS 2026
Poster: Backdoor Attack on Extreme Learning Machines · CCS 2023
Data mining
tabular data		 0.312026
CatBack: Universal Backdoor Attacks on Tabular Data via Categorical Encoding · NDSS 2026
Machine learning › Deep learning architectures and training › feedforward neural network › random feature neural network
extreme learning machine		 0.212023
Poster: Backdoor Attack on Extreme Learning Machines · CCS 2023

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

categorical encoding · 2.0backdoor attack · 1.3
YearPublicationVenuePosition
2026 CatBack: Universal Backdoor Attacks on Tabular Data via Categorical Encoding
Behrad Tajalli, Stefanos Koffas, Stjepan Picek
 NDSS1
2023 Poster: Backdoor Attack on Extreme Learning Machines
abstract
Deep neural networks (DNNs) achieve top performance through costly training on large datasets. Such resources may not be available in some scenarios, like IoT or healthcare. Extreme learning machines (ELMs) aim to alleviate this problem using single-layered networks, requiring fewer training resources. Current investigations have found that DNNs are prone to security and privacy threats, where malfunction of the network or training data extraction can be performed.
Behrad Tajalli, Gorka Abad, Stjepan Picek
 CCS1