7 citations · 14 across the 8 of their papers we have counts for
9 papers
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…
Ultrametric Cluster Hierarchies: I Want 'em All!
Andrew Draganov, Pascal Weber, Rasmus Skibdahl Melanchton Jørgensen +3
Hierarchical clustering is a powerful tool for exploratory data analysis, organizing data into a tree of clusterings from which a partition can be chosen. This paper generalizes th…
Relating tSNE and UMAP to Classical Dimensionality Reduction
Andrew Draganov, Simon Dohn
It has become standard to use gradient-based dimensionality reduction (DR) methods like tSNE and UMAP when explaining what AI models have learned. This makes sense: these methods a…
ActUp: Analyzing and Consolidating tSNE and UMAP
Andrew Draganov, Jakob Rødsgaard Jørgensen, Katrine Scheel Nellemann +4
tSNE and UMAP are popular dimensionality reduction algorithms due to their speed and interpretable low-dimensional embeddings. Despite their popularity, however, little work has be…
GiDR-DUN; Gradient Dimensionality Reduction -- Differences and Unification
Andrew Draganov, Tyrus Berry, Jakob Rødsgaard Jørgensen +3
TSNE and UMAP are two of the most popular dimensionality reduction algorithms due to their speed and interpretable low-dimensional embeddings. However, while attempts have been mad…
UCoDe: Unified Community Detection with Graph Convolutional Networks
Atefeh Moradan, Andrew Draganov, Davide Mottin +1
Community detection finds homogeneous groups of nodes in a graph. Existing approaches either partition the graph into disjoint, non-overlapping, communities, or determine only over…
ChaRRNets: Channel Robust Representation Networks for RF Fingerprinting
Carter N. Brown, Enrico Mattei, Andrew Draganov
We present complex-valued Convolutional Neural Networks (CNNs) for RF fingerprinting that go beyond translation invariance and appropriately account for the inductive bias with res…