Search Results for author:
Found 9 papers, 2 papers with code
Closed-Form Bounds for DP-SGD against Record-level Inference
This paper presents a new approach to evaluate the privacy of machine learning models against specific record-level threats, such as membership and attribute inference, without the indirection through DP.
Maatphor: Automated Variant Analysis for Prompt Injection Attacks
This tool can also assist in generating datasets for jailbreak and prompt injection attacks, thus overcoming the scarcity of data in this domain.
Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective
In this paper, we take an information flow control perspective to describe machine learning systems, which allows us to leverage metadata such as access control policies and define clear-cut privacy and confidentiality guarantees with interpretable information flows.
SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
Deploying machine learning models in production may allow adversaries to infer sensitive information about training data.
Bayesian Estimation of Differential Privacy
Our Bayesian method exploits the hypothesis testing interpretation of differential privacy to obtain a posterior for $\varepsilon$ (not just a confidence interval) from the joint posterior of the false positive and false negative rates of membership inference attacks.
Grey-box Extraction of Natural Language Models
This is true even for queries that are entirely in-distribution, making extraction attacks indistinguishable from legitimate use; (ii) with fine-tuned base layers, the effectiveness of algebraic attacks decreases with the learning rate, showing that fine-tuning is not only beneficial for accuracy but also indispensable for model confidentiality.
Analyzing Information Leakage of Updates to Natural Language Models
To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models.
Analyzing Privacy Loss in Updates of Natural Language Models
To continuously improve quality and reflect changes in data, machine learning-based services have to regularly re-train and update their core models.
Theory and Practice of Finding Eviction Sets
Many micro-architectural attacks rely on the capability of an attacker to efficiently find small eviction sets: groups of virtual addresses that map to the same cache set.
Cryptography and Security
