158 citations · 528 across the 70 of their papers we have counts for
12 papers · 1 filter
Robust and Actively Secure Serverless Collaborative Learning
Olive Franzese, Adam Dziedzic, Christopher A. Choquette-Choo +7
Collaborative machine learning (ML) is widely used to enable institutions to learn better models from distributed data. While collaborative approaches to learning intuitively prote…
Beyond Labeling Oracles: What does it mean to steal ML models?
Avital Shafran, Ilia Shumailov, Murat A. Erdogdu +1
Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. Machine Learning (ML)…
LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
David Glukhov, Ilia Shumailov, Yarin Gal +2
Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concer…
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
Anvith Thudi, Hengrui Jia, Casey Meehan +2
Differentially private stochastic gradient descent (DP-SGD) is the canonical approach to private deep learning. While the current privacy analysis of DP-SGD is known to be tight in…
Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
Jiapeng Wu, Atiyeh Ashari Ghomi, David Glukhov +3
Machine learning models are susceptible to a variety of attacks that can erode trust, including attacks against the privacy of training data, and adversarial examples that jeopardi…
When Vision Fails: Text Attacks Against ViT and OCR
Nicholas Boucher, Jenny Blessing, Ilia Shumailov +2
Text-based machine learning models are vulnerable to an emerging class of Unicode-based adversarial examples capable of tricking a model into misreading text with potentially disas…
Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
Haonan Duan, Adam Dziedzic, Nicolas Papernot +1
Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these conce…
The Curse of Recursion: Training on Generated Data Makes Models Forget
Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao +3
Stable Diffusion revolutionised image creation from descriptive text. GPT-2, GPT-3(.5) and GPT-4 demonstrated astonishing performance across a variety of language tasks. ChatGPT in…
Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
Rachel Cummings, Damien Desfontaines, David Evans +21
In this article, we present a detailed review of current practices and state-of-the-art methodologies in the field of differential privacy (DP), with a focus of advancing DP's depl…
Have it your way: Individualized Privacy Assignment for DP-SGD
Franziska Boenisch, Christopher Mühl, Adam Dziedzic +2
When training a machine learning model with differential privacy, one sets a privacy budget. This budget represents a maximal privacy violation that any user is willing to face by…
Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility
Mohammad Yaghini, Patty Liu, Franziska Boenisch +1
Deploying machine learning (ML) models often requires both fairness and privacy guarantees. Both of these objectives present unique trade-offs with the utility (e.g., accuracy) of…
Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation
Franziska Boenisch, Adam Dziedzic, Roei Schuster +3
Federated learning (FL) is a framework for users to jointly train a machine learning model. FL is promoted as a privacy-enhancing technology (PET) that provides data minimization:…