6 papers
MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks
Jona te Lintelo, Lichao Wu, Marina KrÄek +2
Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradig…
Backdoor Attacks on Decentralised Post-Training
OÄuzhan 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…
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…
Interpreting Emergent Features in Deep Learning-based Side-channel Analysis
Sengim Karayalçin, Marina KrÄek, 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…
SoK: The Last Line of Defense: On Backdoor Defense Evaluation
Gorka Abad, Marina KrÄek, 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…
NoMod: A Non-modular Attack on Module Learning With Errors
Cristian Bassotto, Ermes Franch, Marina KrÄek +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…