10 papers
SoK: Colluding Adversaries in Machine Learning Pipelines
Vasisht Duddu, Lipeng He, Asim Waheed +1
Machine learning (ML) models are susceptible to various security, privacy, and fairness risks. Adversaries with different characteristics (i.e., objectives, knowledge, and capabili…
PAL*M: Property Attestation for Large Generative Models
Prach Chantasantitam, Adam Ilyas Caulfield, Vasisht Duddu +2
Machine learning property attestations allow provers (e.g., model providers or owners) to attest properties of their models/datasets to verifiers (e.g., regulators, customers), ena…
Locket: Robust Feature-Locking Technique for Language Models
Lipeng He, Vasisht Duddu, N. Asokan
Chatbot service providers (e.g., OpenAI) rely on tiered subscription plans to generate revenue, offering black-box access to basic models for free users and advanced models to payi…
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…
Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
Yan Shvartzshnaider, Vasisht Duddu
As large language models (LLMs) are integrated into sociotechnical systems, it is crucial to examine the privacy biases they exhibit. We define privacy bias as the appropriateness…
Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
Asim Waheed, Vasisht Duddu, Rui Zhang +1
Machine learning (ML) models are susceptible to various risks to security, privacy, and fairness. Most defenses are designed to protect against each risk individually (intended int…