A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
SOTERIA optimizes neural networks for secure inference with minimal overhead.
Paper tackles efficient HMM learning with conditional samples.
In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we argued that adversarial examples in machine learning might be due to an inherent computational hardness of the problem. More precisely, we constructed a binary classification task for which (i) a robust classifier exists; yet no non-trivial accuracy c…
We discuss some applications of 3-manifold topology to cryptography. In particular, we propose a public-key and a symmetric-key cryptographic scheme based on the Thurston norm on the first cohomology of hyperbolic manifolds.
Privacy concern has been increasingly important in many machine learning (ML) problems. We study empirical risk minimization (ERM) problems under secure multi-party computation (MPC) frameworks. Main technical tools for MPC have been developed based on cryptography. One of limitations in current cryptographically priva…
Boosting algorithm reduces error in noisy data.
Reduces learning periodic neural networks to lattice problems, proving hardness under cryptographic assumptions.
We continue the study of statistical/computational tradeoffs in learning robust classifiers, following the recent work of Bubeck, Lee, Price and Razenshteyn who showed examples of classification tasks where (a) an efficient robust classifier exists, in the small-perturbation regime; (b) a non-robust classifier can be l…
Origami uses SGX enclaves and blinding to protect deep neural network inference privacy.
PHAZE framework uses zkML and hashing for fast, verifiable LHC trigger decisions.
Study learning from multiple thinkers providing step-by-step solutions to problems.
How to train a machine learning model while keeping the data private and secure? We present CodedPrivateML, a fast and scalable approach to this critical problem. CodedPrivateML keeps both the data and the model information-theoretically private, while allowing efficient parallelization of training across distributed w…
Quantum crypto-economics models price risks in blockchain technology.
Safe-House secures DeFi by limiting losses and enhancing security.
This paper strengthens the computational separation between multimodal and unimodal learning, showing unimodal learning is hard on typical instances.
Paper proposes scalable privacy-preserving DNN for industrial applications.
As neural networks revolutionize many applications, significant privacy conflicts between model users and providers emerge. The cryptography community developed a variety of techniques for secure computation to address such privacy issues. As generic techniques for secure computation are typically prohibitively ineffec…
AriaNN enables private deep learning with minimal interaction and reduced key sizes.
Hard to estimate -accurate scores without strong assumptions.
Local regularization fails in transductive learning for some multiclass problems.
Approach to verify neural network training integrity.
Framework certifies fairness of machine learning models interactively and privately.
In the last decade, deep learning algorithms have become very popular thanks to the achieved performance in many machine learning and computer vision tasks. However, most of the deep learning architectures are vulnerable to so called adversarial examples. This questions the security of deep neural networks (DNN) for ma…
Quantum computers outperform classical methods in density modeling.
Federated learning platform for drug discovery without sharing data.
CryptoNAS improves PI accuracy by 3.4% with 2.4x less latency.
There are recent cryptographic protocols that are based on Multiple Simultaneous Conjugacy Problems in braid groups. We improve an algorithm, due to Sang Jin Lee and Eonkyung Lee, to solve these problems, by applying a method developed by the author and Nuno Franco, originally intended to solve the Conjugacy Search Pro…
Privacy is a major issue in learning from distributed data. Recently the cryptographic literature has provided several tools for this task. However, these tools either reduce the quality/accuracy of the learning algorithm---e.g., by adding noise---or they incur a high performance penalty and/or involve trusting externa…
New findings suggest minimax optimality doesn't guarantee distribution learning for GANs.
Paper addresses federated contextual bandits with encryption.
The fifth generation (5G) and beyond wireless networks are critical to support diverse vertical applications by connecting heterogeneous devices and machines, which directly increase vulnerability for various spoofing attacks. Conventional cryptographic and physical layer authentication techniques are facing some chall…
We discuss several uses of blockchain (and, more generally, distributed ledger) technologies outside of cryptocurrencies with a pragmatic view. We mostly focus on three areas: the role of coin economies for what we refer to as data malls (specialized data marketplaces); data provenance (a historical record of data and …
Study on computational aspects of replicable learning, bridging statistical and algorithmic perspectives.
Advances in fractional analysis suggest a new way for the physics understanding of Riemann's conjecture. It asserts that, if s is a complex number, the non trivial zeros of zeta function in the gap [0,1], is characterized by . This conjecture can be understood as a consequence of 1/2-order fractional differential chara…
Safeguarding privacy in machine learning is highly desirable, especially in collaborative studies across many organizations. Privacy-preserving distributed machine learning (based on cryptography) is popular to solve the problem. However, existing cryptographic protocols still incur excess computational overhead. Here,…
Post-quantum cryptography needed for blockchain security.
We propose a new randomized ensemble technique with a provable security guarantee against black-box transfer attacks. Our proof constructs a new security problem for random binary classifiers which is easier to empirically verify and a reduction from the security of this new model to the security of the ensemble classi…
This study calculates the maximum error of a famous estimation method.
Proposes measuring fairness through multiple stakeholder-curated stress tests.
Over recent years, devising classification algorithms that are robust to adversarial perturbations has emerged as a challenging problem. In particular, deep neural nets (DNNs) seem to be susceptible to small imperceptible changes over test instances. However, the line of work in provable robustness, so far, has been fo…
The key cryptographic protocols used to secure the internet and financial transactions of today are all susceptible to attack by the development of a sufficiently large quantum computer. One particular area at risk are cryptocurrencies, a market currently worth over 150 billion USD. We investigate the risk of Bitcoin, …
Neural Networks (NN) have recently emerged as backbone of several sensitive applications like automobile, medical image, security, etc. NNs inherently offer Partial Fault Tolerance (PFT) in their architecture; however, the biased PFT of NNs can lead to severe consequences in applications like cryptography and security …
Proves SQ lower bounds for learning two-hidden-layer neural networks.
We present two new statistical machine learning methods designed to learn on fully homomorphic encrypted (FHE) data. The introduction of FHE schemes following Gentry (2009) opens up the prospect of privacy preserving statistical machine learning analysis and modelling of encrypted data without compromising security con…
Paper investigates hardness of learning neural networks under manifold hypothesis.
Novel algorithm for privacy-preserving distributed learning in analog domain.
A scalable protocol for federated averaging with privacy and correctness guarantees.
Hardness proven for learning neural networks with polynomial size and Gaussian inputs.