7 citations · 14 across the 8 of their papers we have counts for
3 papers · 1 filter
Stress-testing Alignment Midtraining
Sid Baines, Jonathan Bostock, Maria Angelica Martinez +3
When aligning frontier models through post-training techniques, it is not possible to directly demonstrate all of the behaviours we want a model to exhibit in all possible deployme…
ToxScreen: Detecting Whether an LLM Has Been Poisoned
Anthony Hughes, Nicole Xing, Collin Francel +2
As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behav…
Phantom Transfer: Data Poisoning can Survive Data-Level Defences
Andrew Draganov, Tolga H. Dur, Anandmayi Bhongade +1
We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot…