1 citations · 1 across the 3 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
Lukas Struppek, Adam Gleave, Kellin Pelrine
As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight mo…
cs.CR2023
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data
Lukas Struppek, Martin B. Hentschel, Clifton Poth +2
Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent dur…