158 citations · 528 across the 70 of their papers we have counts for
14 papers · 1 filter
Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification
Carter Luck, Olive Franzese-McLaughlin, Elisaweta Masserova +3
Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing their internals or training da…
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
Stephan Rabanser, Ali Shahin Shamsabadi, Olive Franzese +3
Cautious predictions -- where a machine learning model abstains when uncertain -- are crucial for limiting harmful errors in safety-critical applications. In this work, we identify…
Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses
David Glukhov, Ziwen Han, Ilia Shumailov +2
Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety…
Architectural Neural Backdoors from First Principles
Harry Langford, Ilia Shumailov, Yiren Zhao +2
While previous research backdoored neural networks by changing their parameters, recent work uncovered a more insidious threat: backdoors embedded within the definition of the netw…
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…
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…
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:…
Learned-Database Systems Security
Roei Schuster, Jin Peng Zhou, Thorsten Eisenhofer +2
A learned database system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learn…
Generative Extraction of Audio Classifiers for Speaker Identification
Tejumade Afonja, Lucas Bourtoule, Varun Chandrasekaran +2
It is perhaps no longer surprising that machine learning models, especially deep neural networks, are particularly vulnerable to attacks. One such vulnerability that has been well…
Increasing the Cost of Model Extraction with Calibrated Proof of Work
Adam Dziedzic, Muhammad Ahmad Kaleem, Yu Shen Lu +1
In model extraction attacks, adversaries can steal a machine learning model exposed via a public API by repeatedly querying it and adjusting their own model based on obtained predi…
SoK: Machine Learning Governance
Varun Chandrasekaran, Hengrui Jia, Anvith Thudi +3
The application of machine learning (ML) in computer systems introduces not only many benefits but also risks to society. In this paper, we develop the concept of ML governance to…
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
Sanghyun Hong, Varun Chandrasekaran, Yiğitcan Kaya +2
Machine learning algorithms are vulnerable to data poisoning attacks. Prior taxonomies that focus on specific scenarios, e.g., indiscriminate or targeted, have enabled defenses for…
Entangled Watermarks as a Defense against Model Extraction
Hengrui Jia, Christopher A. Choquette-Choo, Varun Chandrasekaran +1
Machine learning involves expensive data collection and training procedures. Model owners may be concerned that valuable intellectual property can be leaked if adversaries mount mo…
Machine Unlearning
Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo +5
Once users have shared their data online, it is generally difficult for them to revoke access and ask for the data to be deleted. Machine learning (ML) exacerbates this problem bec…