7 papers
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…
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…
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…
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…
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…