5 papers
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…
Boundary-targeted Membership Inference Attacks on Safety Classifiers
Anthony Hughes, Alexander Goldberg, Prince Jha +3
Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despit…
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…
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…
Identifying and Aligning Medical Claims Made on Social Media with Medical Evidence
Anthony Hughes, Xingyi Song
Evidence-based medicine is the practice of making medical decisions that adhere to the latest, and best known evidence at that time. Currently, the best evidence is often found in…