3 papers
cs.CR2026
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…
cs.CR2025
PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing
Anthony Hughes, Vasisht Duddu, N. Asokan +2
Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms su…
cs.CL2024
How Private are Language Models in Abstractive Summarization?
Anthony Hughes, Ning Ma, Nikolaos Aletras
In sensitive domains such as medical and legal, protecting sensitive information is critical, with protective laws strictly prohibiting the disclosure of personal data. This poses…