Behrad Tajalli

According to our database, Behrad Tajalli authored at least 7 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Backdoors on Manifold Learning.

Christina Kreza, Stefanos Koffas, Behrad Tajalli, Mauro Conti, Stjepan Picek

Proceedings of the 2024 ACM Workshop on Wireless Security and Machine Learning, 2024

Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attacks.

Xiaoyun Xu, Oguzhan Ersoy, Behrad Tajalli, Stjepan Picek

Proceedings of the 54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, 2024

ELMs Under Siege: A Study on Backdoor Attacks on Extreme Learning Machines.

Behrad Tajalli, Stefanos Koffas, Gorka Abad, Stjepan Picek

Proceedings of the 2024 Workshop on Artificial Intelligence and Security, 2024

2023

Tabdoor: Backdoor Vulnerabilities in Transformer-based Neural Networks for Tabular Data.

Bart Pleiter, Behrad Tajalli, Stefanos Koffas, Gorka Abad, Jing Xu, Martha A. Larson, Stjepan Picek

CoRR, 2023

A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification.

Gorka Abad, Jing Xu, Stefanos Koffas, Behrad Tajalli, Stjepan Picek

CoRR, 2023

On Feasibility of Server-side Backdoor Attacks on Split Learning.

Behrad Tajalli, Oguzhan Ersoy, Stjepan Picek

Proceedings of the 2023 IEEE Security and Privacy Workshops (SPW), 2023

Poster: Backdoor Attack on Extreme Learning Machines.

Behrad Tajalli, Gorka Abad, Stjepan Picek

Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023