The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces
Year: 2026
Type: conference-paper
Abstract: Angelina Tsai, Shreya Subramanian, Catherine Liu, Kimberly Lopez, Leif Zinn-Brooks, Alexia E. Schulz, Adaku Uchendu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop). 2026.
Institutions: Harvey Mudd College, MIT Lincoln Laboratory
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G4694536500
OpenAlex ID: W7166843763