Follow the ideas that keep turning up in Hacker News discussions.
Luca Beurer-Kellner, Beat Buesser, Ana-Maria Creţu +11
As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge.
Ross Mcilroy, Jaroslav Sevcik, Tobias Tebbi +2
The recent discovery of the Spectre and Meltdown attacks represents a watershed moment not just for the field of Computer Security, but also of Programming Languages.
Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy
Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence.
John C. Baez, Mike Stay
In physics, Feynman diagrams are used to reason about quantum processes.
Nicholas Carlini, Jamie Hayes, Milad Nasr +6
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have attracted significant attention due to their ability to generate high-quality synthetic images.
Craig Gidney
Planning the transition to quantum-safe cryptosystems requires understanding the cost of quantum attacks on vulnerable cryptosystems.
Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi +1
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability.
Malte Möser, Kyle Soska, Ethan Heilman +8
Monero is a privacy-centric cryptocurrency that allows users to obscure their transactions by including chaff coins, called "mixins," along with the actual coins they spend.
Martín Abadi, Andy Chu, Ian Goodfellow +4
Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains.
Mark Chen, Jerry Tworek, Heewoo Jun +55
We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities.
Craig Gidney, Martin Ekerå
We significantly reduce the cost of factoring integers and computing discrete logarithms in finite fields on a quantum computer by combining techniques from Shor 1994, Griffiths-Niu 1996, Zalka 2006, Fowler 2012, Ekerå-Håstad 2017, Ekerå 2017, Ekerå 2018, Gidney-Fowler 2019, Gidney 2019.
Ittay Eyal, Emin Gun Sirer
The Bitcoin cryptocurrency records its transactions in a public log called the blockchain.
Hans Niklas Jacob, Christian Werling, Robert Buhren +1
Trusted Platform Modules constitute an integral building block of modern security features.
Norman P. Jouppi, George Kurian, Sheng Li +11
In response to innovations in machine learning (ML) models, production workloads changed radically and rapidly.
Edoardo Debenedetti, Ilia Shumailov, Tianqi Fan +7
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment.
Jarek Duda
The modern data compression is mainly based on two approaches to entropy coding: Huffman (HC) and arithmetic/range coding (AC).
Yves-Alexandre de Montjoye, César A. Hidalgo, Michel Verleysen +1
Yann Dauphin, Razvan Pascanu, Caglar Gulcehre +3
A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces.
Jan Betley, Daniel Tan, Niels Warncke +5
We present a surprising result regarding LLMs and alignment.
Fergal Reid, Martin Harrigan
Anonymity in Bitcoin, a peer-to-peer electronic currency system, is a complicated issue.
Marino Miculan, Nicola Vitacolonna
MTProto 2.0 is a suite of cryptographic protocols for instant messaging at the core of the popular Telegram messenger application.
Jiaqi Geng, Dong Huang, Fernando De la Torre
Advances in computer vision and machine learning techniques have led to significant development in 2D and 3D human pose estimation from RGB cameras, LiDAR, and radars.
Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian +2
Large Language Models (LLMs) perform impressively well in various applications.
Lieven M. K. Vandersypen, Matthias Steffen, Gregory Breyta +3
The number of steps any classical computer requires in order to find the prime factors of an $l$-digit integer $N$ increases exponentially with $l$, at least using algorithms known at present.
Scott A. Kulp, Benjamin H. Strauss
Abstract Most estimates of global mean sea-level rise this century fall below 2 m.
Nicolas Papernot, Patrick McDaniel, Ian Goodfellow +3
Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers.
Jeremy Martin, Travis Mayberry, Collin Donahue +5
MAC address randomization is a privacy technique whereby mobile devices rotate through random hardware addresses in order to prevent observers from singling out their traffic or physical location from other nearby devices.
Hui Xu, Zhuangbin Chen, Mingshen Sun +2
Rust is an emerging programing language that aims at preventing memory-safety bugs without sacrificing much efficiency.
Nicholas Carlini, Daphne Ippolito, Matthew Jagielski +3
Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim.
Jiska Classen, Alexander Heinrich, Robert Reith +1
When an iPhone is turned off, most wireless chips stay on.