collaborators

6 papers

cs.CR2026

MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks

Jona te Lintelo, Lichao Wu, Marina Krček +2

Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradig…

cs.CR2026

Backdoor Attacks on Decentralised Post-Training

Oğuzhan Ersoy, Nikolay Blagoev, Jona te Lintelo +3

Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training c…

cs.CV2026

Backdoor Directions in Vision Transformers

Sengim Karayalcin, Marina Krcek, Pin-Yu Chen +1

This paper investigates how Backdoor Attacks are represented within Vision Transformers (ViTs). By assuming knowledge of the trigger, we identify a specific ``trigger direction'' i…

cs.CR2025

Interpreting Emergent Features in Deep Learning-based Side-channel Analysis

Sengim Karayalçin, Marina Krček, Stjepan Picek

Side-channel analysis (SCA) poses a real-world threat by exploiting unintentional physical signals to extract secret information from secure devices. Evaluation labs also use the s…

cs.CR2025

SoK: The Last Line of Defense: On Backdoor Defense Evaluation

Gorka Abad, Marina Krček, Stefanos Koffas +7

Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been…

cs.CR2025

NoMod: A Non-modular Attack on Module Learning With Errors

Cristian Bassotto, Ermes Franch, Marina Krček +1

The advent of quantum computing threatens classical public-key cryptography, motivating NIST's adoption of post-quantum schemes such as those based on the Module Learning With Erro…