2 papers
cs.CR2026
Steganography Without Modification: Hidden Communication via LLM Seeds
Felix Mächtle, Jonas Sander, Sebastian Berndt +3
We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or ou…
cs.LG2026
Non-omniscient backdoor injection with one poison sample: Proving the one-poison hypothesis for linear regression, linear classification, and 2-layer ReLU neural networks
Thorsten Peinemann, Paula Arnold, Sebastian Berndt +2
Backdoor poisoning attacks are a threat to machine learning models trained on large data collected from untrusted sources; these attacks enable attackers to inject malicious behavi…