Papers by Catherine Liu
The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces (2026.acl-srw)
Copied to clipboard
Angelina Tsai, Shreya Subramanian, Catherine Liu, Kimberly Lopez, Leif Zinn-Brooks, Alexia E. Schulz, Adaku Uchendu
| Challenge: | Large Language Models (LLMs) have unprecedented capabilities, but they pose security concerns . current adversarial attacks exploit vulnerabilities in the embedding space of language models, allowing attackers to bypass safety guardrails and cause significant harmful consequences. |
| Approach: | They propose to use topological data analysis to characterize how adversarial perturbations act on text inputs by computing persistent homology metrics from attention maps across different model architectures. |
| Outcome: | The proposed visualizations show that adversarial perturbations alter higher-dimensional topological features in ways that distinguish them from clean, non-adversarial inputs. |
Annotating Interruption in Dyadic Human Interaction (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing interruption and turn switch classification methods are not yet available. |
| Approach: | They propose a new interruption annotation schema that integrates existing interruption and turn switch classification methods to annotate different types of interruptions. |
| Outcome: | The proposed method can distinguish smooth turn exchange, backchannel and interruption (including interruption types) and to annotate dyadic conversation. |