collaborators

7 papers

cs.CR2026

SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation

Xiaoyun Xu, Lichao Wu, Jona te Lintelo +2

Large language models routinely generate code with exploitable security flaws. Prior literature attributes this limitation to a lack of security expertise, steering current defense…

cs.CR2026

GoodVibe: Security-by-Vibe for LLM-Based Code Generation

Maximilian Thang, Lichao Wu, Sasha Behrouzi +4

Large language models (LLMs) are increasingly used for code generation in fast, informal development workflows, often referred to as vibe coding, where speed and convenience are pr…

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.CR2026

Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert Silencing

Jona te Lintelo, Lichao Wu, Stjepan Picek

The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve scaling efficiency by activatin…

cs.CR2026

BadPatches: Routing-aware Backdoor Attacks on Vision Mixture of Experts

Cedric Chan, Jona te Lintelo, Stjepan Picek

Mixture of Experts (MoE) architectures have gained popularity for reducing computational costs in deep neural networks by activating only a subset of parameters during inference. W…