Sam Gunn
YOU?
Author Swipe
View article: SoK: Watermarking for AI-Generated Content
SoK: Watermarking for AI-Generated Content Open
As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are a promising approach to address the problem of distinguishi…
View article: Ideal Pseudorandom Codes
Ideal Pseudorandom Codes Open
Pseudorandom codes are error-correcting codes with the property that no efficient adversary can distinguish encodings from uniformly random strings. They were recently introduced by Christ and Gunn [CRYPTO 2024] for the purpose of watermar…
View article: Quantum One-Time Protection of any Randomized Algorithm
Quantum One-Time Protection of any Randomized Algorithm Open
The meteoric rise in power and popularity of machine learning models dependent on valuable training data has reignited a basic tension between the power of running a program locally and the risk of exposing details of that program to the u…
View article: An Undetectable Watermark for Generative Image Models
An Undetectable Watermark for Generative Image Models Open
We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many adaptive queries. …
View article: Approaching the Quantum Singleton Bound with Approximate Error Correction
Approaching the Quantum Singleton Bound with Approximate Error Correction Open
It is well known that no quantum error correcting code of rate R can correct adversarial errors on more than a (1−R)/4 fraction of symbols. But what if we only require our codes to approximately recover the message?
View article: How to Use Quantum Indistinguishability Obfuscation
How to Use Quantum Indistinguishability Obfuscation Open
Quantum copy protection, introduced by Aaronson, enables giving out a quantum program-description that cannot be meaningfully duplicated. Despite over a decade of study, copy protection is only known to be possible for a very limited class…
View article: Classical Commitments to Quantum States
Classical Commitments to Quantum States Open
We define the notion of a classical commitment scheme to quantum states, which allows a quantum prover to compute a classical commitment to a quantum state, and later open each qubit of the state in either the standard or the Hadamard basi…
View article: Pseudorandom Error-Correcting Codes
Pseudorandom Error-Correcting Codes Open
We construct pseudorandom error-correcting codes (or simply pseudorandom codes), which are error-correcting codes with the property that any polynomial number of codewords are pseudorandom to any computationally-bounded adversary. Efficien…
View article: How to Use Quantum Indistinguishability Obfuscation
How to Use Quantum Indistinguishability Obfuscation Open
Quantum copy protection, introduced by Aaronson, enables giving out a quantum program-description that cannot be meaningfully duplicated. Despite over a decade of study, copy protection is only known to be possible for a very limited class…
View article: Undetectable Watermarks for Language Models
Undetectable Watermarks for Language Models Open
Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing concern about our ability to detect AI-generated text. Prior works have suggested methods of embedding watermarks in model outputs, by notic…
View article: Commitments to Quantum States
Commitments to Quantum States Open
What does it mean to commit to a quantum state? In this work, we propose a simple answer: a commitment to quantum messages is binding if, after the commit phase, the committed state is hidden from the sender's view. We accompany this new d…
View article: Is Untrusted Randomness Helpful?
Is Untrusted Randomness Helpful? Open
Randomized algorithms and protocols assume the availability of a perfect source of randomness. In real life, however, perfect randomness is rare and is almost never guaranteed. The gap between these two facts motivated much of the work on …
View article: Approaching the Quantum Singleton Bound with Approximate Error Correction
Approaching the Quantum Singleton Bound with Approximate Error Correction Open
It is well known that no quantum error correcting code of rate $R$ can correct adversarial errors on more than a $(1-R)/4$ fraction of symbols. But what if we only require our codes to *approximately* recover the message? We construct effi…
View article: Adversarial poisoning attacks on reinforcement learning-driven energy pricing
Adversarial poisoning attacks on reinforcement learning-driven energy pricing Open
Complex controls are increasingly common in power systems. Reinforcement learning (RL) has emerged as a strong candidate for implementing various controllers. One common use of RL in this context is for prosumer pricing aggregations, where…
View article: Commitments to Quantum States
Commitments to Quantum States Open
What does it mean to commit to a quantum state? In this work, we propose a simple answer: a commitment to quantum messages is binding if, after the commit phase, the committed state is hidden from the sender's view. We accompany this new d…
View article: On Certified Randomness from Quantum Advantage Experiments.
On Certified Randomness from Quantum Advantage Experiments. Open
Certified randomness has a long history in quantum information, with many potential applications. Recently Aaronson (Aaronson 2018, 2020) proposed a novel certified randomness protocol based on existing random circuit sampling (RCS) experi…
View article: Review of a Quantum Algorithm for Betti Numbers
Review of a Quantum Algorithm for Betti Numbers Open
We looked into the algorithm for calculating Betti numbers presented by Lloyd, Garnerone, and Zanardi (LGZ). We present a new algorithm in the same spirit as LGZ with the intent of clarifying quantum algorithms for computing Betti numbers.…