Search Results for author:
Found 7 papers, 1 papers with code
Publicly Detectable Watermarking for Language Models
We construct the first provable watermarking scheme for language models with public detectability or verifiability: we use a private key for watermarking and a public key for watermark detection.
Overparameterization from Computational Constraints
In particular, for computationally bounded learners, we extend the recent result of Bubeck and Sellke [NeurIPS'2021] which shows that robust models might need more parameters, to the computational regime and show that bounded learners could provably need an even larger number of parameters.
Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning
Privacy attacks on machine learning models aim to identify the data that is used to train such models.
Is Private Learning Possible with Instance Encoding?
A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy.
A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks
Some of the stronger poisoning attacks require the full knowledge of the training data.
Formalizing Data Deletion in the Context of the Right to be Forgotten
In particular, we provide a precise definition of what could be (or should be) expected from an entity that collects individuals' data when a request is made of it to delete some of this data.
Cryptography and Security
Adversarially Robust Learning Could Leverage Computational Hardness
On the reverse directions, we also show that the existence of such learning task in which computational robustness beats information theoretic robustness requires computational hardness by implying (average-case) hardness of NP.
