7 papers
Hasse Obstructions to Rationality for Special Fourfolds
Aideen Fay
For every nonempty Hassett divisor parameterizing special cubic fourfolds, we consider the quaternion class in the two-torsion Brauer group. We prove…
An atomic criterion for irrationality without quantum computations
Vladimiro Benedetti, Aideen Fay, Jérémy Guéré +2
The birational invariants introduced by Katzarkov-Kontsevich-Pantev-Yu allows one to obtain irrationality results for varieties whose quantum cohomology is well-behaved. We observe…
The Very General Verra Fourfold is Irrational
Aideen Fay
We show that the very general Verra fourfold is irrational, using the Hodge atom framework of Katzarkov--Kontsevich--Pantev--Yu. Two novel points are: a refined analysis of Hodge a…
Equivariant irrationality of very general symmetric Verra fourfolds
Aideen Fay
We prove that a very general complex symmetric Verra fourfold is not \(\ZZ/2\)-birational to \(\PP^4\), using the \emph{theory of atoms} introduced by Katzarkov--Kontsevich--Pantev…
LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
Sahar Abdelnabi, Aideen Fay, Ahmed Salem +22
Indirect prompt injection attacks exploit a fundamental weakness of LLMs: executing unauthorized tasks from untrusted sources. Despite the practical significance of this attack vec…
The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology
Aideen Fay, Inés García-Redondo, Qiquan Wang +2
Existing interpretability methods for Large Language Models (LLMs) predominantly capture linear directions or isolated features. This overlooks the high-dimensional, relational, an…
Get my drift? Catching LLM Task Drift with Activation Deltas
Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin +3
LLMs are commonly used in retrieval-augmented applications to execute user instructions based on data from external sources. For example, modern search engines use LLMs to answer q…