92 citations · 211 across the 21 of their papers we have counts for
27 papers
KNOX: Hardware-assisted Regulatory Sandbox for Generative Models
Vasisht Duddu, Adam Caulfield, Xi He
Regulations require companies to run AI models in a regulatory sandbox, an isolated environment that enables monitoring model behavior by regulators, prior to deployment. But, they…
Trusted Model Environment for Private Semantic Computations
Vasisht Duddu, Xi He
A private semantic computation primitive enables parties to privately compute over structured and unstructured data that requires understanding its semantics, context, and relation…
"People can change, and patterns can be broken": Contextualizing Tradeoffs in Automated Decision-Making Systems
Rabeya Bosri, Anna Harbluk Lorimer, Afrida Hossain +2
Automated decision-making (ADM) systems are increasingly deployed in domains such as mortgage lending, prison sentencing, health insurance coverage, and hiring. Designing a respons…
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…
Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
Asim Waheed, Vasisht Duddu, Sebastian Szyller
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…
Position: Contextual Integrity is Inadequately Applied to Language Models
Yan Shvartzshnaider, Vasisht Duddu
Machine learning community is discovering Contextual Integrity (CI) as a useful framework to assess the privacy implications of large language models (LLMs). This is an encouraging…
Combining Machine Learning Defenses without Conflicts
Vasisht Duddu, Rui Zhang, N. Asokan
Machine learning (ML) defenses protect against various risks to security, privacy, and fairness. Real-life models need simultaneous protection against multiple different risks whic…
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…
Laminator: Verifiable ML Property Cards using Hardware-assisted Attestations
Vasisht Duddu, Oskari Järvinen, Lachlan J Gunn +1
Regulations increasingly call for various assurances from machine learning (ML) model providers about their training data, training process, and model behavior. For better transpar…
Espresso: Robust Concept Filtering in Text-to-Image Models
Anudeep Das, Vasisht Duddu, Rui Zhang +1
Diffusion based text-to-image models are trained on large datasets scraped from the Internet, potentially containing unacceptable concepts (e.g., copyright-infringing or unsafe). W…
SoK: Unintended Interactions among Machine Learning Defenses and Risks
Vasisht Duddu, Sebastian Szyller, N. Asokan
Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mit…
Attesting Distributional Properties of Training Data for Machine Learning
Vasisht Duddu, Anudeep Das, Nora Khayata +3
The success of machine learning (ML) has been accompanied by increased concerns about its trustworthiness. Several jurisdictions are preparing ML regulatory frameworks. One such co…
GrOVe: Ownership Verification of Graph Neural Networks using Embeddings
Asim Waheed, Vasisht Duddu, N. Asokan
Graph neural networks (GNNs) have emerged as a state-of-the-art approach to model and draw inferences from large scale graph-structured data in various application settings such as…
On the Alignment of Group Fairness with Attribute Privacy
Jan Aalmoes, Vasisht Duddu, Antoine Boutet
Group fairness and privacy are fundamental aspects in designing trustworthy machine learning models. Previous research has highlighted conflicts between group fairness and differen…
Comprehension from Chaos: Towards Informed Consent for Private Computation
Bailey Kacsmar, Vasisht Duddu, Kyle Tilbury +2
Private computation, which includes techniques like multi-party computation and private query execution, holds great promise for enabling organizations to analyze data they and the…
Inferring Sensitive Attributes from Model Explanations
Vasisht Duddu, Antoine Boutet
Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to i…
Dikaios: Privacy Auditing of Algorithmic Fairness via Attribute Inference Attacks
Jan Aalmoes, Vasisht Duddu, Antoine Boutet
Machine learning (ML) models have been deployed for high-stakes applications. Due to class imbalance in the sensitive attribute observed in the datasets, ML models are unfair on mi…
SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning
Vasisht Duddu, Sebastian Szyller, N. Asokan
Data used to train machine learning (ML) models can be sensitive. Membership inference attacks (MIAs), attempting to determine whether a particular data record was used to train an…
Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Models
Sebastian Szyller, Vasisht Duddu, Tommi Gröndahl +1
Machine learning models are typically made available to potential client users via inference APIs. Model extraction attacks occur when a malicious client uses information gleaned f…
GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning
Vasisht Duddu, Antoine Boutet, Virat Shejwalkar
Embedded systems demand on-device processing of data using Neural Networks (NNs) while conforming to the memory, power and computation constraints, leading to an efficiency and acc…
Quantifying Privacy Leakage in Graph Embedding
Vasisht Duddu, Antoine Boutet, Virat Shejwalkar
Graph embeddings have been proposed to map graph data to low dimensional space for downstream processing (e.g., node classification or link prediction). With the increasing collect…