Secure method provides guarantees for approximate solutions in cryptographically private ML.
problem Computational intractability of evaluating non-linear functions in cryptographically private ML.
method Secure Approximation Guarantee (SAG) method.
result SAG method provides a non-probabilistic bound on the approximation quality.
Origami uses SGX enclaves and blinding to protect deep neural network inference privacy.
problem Protecting deep neural network inference privacy in machine learning services.
method Combines enclave execution, cryptographic blinding, and accelerator-based computation.
result Demonstrates improved privacy-preserving inference performance compared to prior work.
Paper proposes scalable privacy-preserving DNN for industrial applications.
problem Data isolation and scalability issues in deep neural networks.
method Split computation graph into private and neutral server parts; use cryptographic techniques for private data.
result Demonstrates practicality of the proposed scalable privacy-preserving DNN.
PD-ML-Lite uses lightweight cryptography for private distributed machine learning.
problem Privacy issues in learning from distributed data.
method Applying lightweight cryptographic protocols to build learning algorithms.
result Achieves the same accuracy as non-private methods while maintaining privacy.
Framework certifies fairness of machine learning models interactively and privately.
problem Certifying fairness of machine learning models in privacy-preserving scenarios.
method Interactive test with cryptographic techniques for fairness certification.
result Empirical evaluation of fairness for various models and definitions.
Biscotti uses blockchain for secure peer-to-peer ML without central coordination.
problem Secure and private multi-party machine learning with trust and poisoning attacks.
method Decentralized peer-to-peer ML using blockchain and cryptography.
result Biscotti protects privacy and model performance against 30% adversaries.
CodedPrivateML secures ML training data and models.
problem Training machine learning models while keeping data private.
method Data and model-theoretically private approach with parallelization.
result Significant speedup over cryptographic methods.
CryptoNAS improves PI accuracy by 3.4% with 2.4x less latency.
problem Private inference on machine learning models with limited latency.
method Developed CryptoNAS, a novel NAS method for finding models that maximize accuracy within a ReLU budget.
result Improves accuracy by 3.4% and latency by 2.4x over state-of-the-art methods.
Paper introduces privacy-preserving few-shot learning for images.
problem Privacy risk in few-shot learning systems.
method Discrete embedding vectors and one-way hash functions.
result Achieves computational pan privacy without storing embeddings.
AriaNN enables private deep learning with minimal interaction and reduced key sizes.
problem Private deep learning with minimal interaction and reduced key sizes.
method Semi-honest 2-party computation protocol with function secret sharing, optimized primitives for neural network operations.
result Efficient private comparison for ReLU operations with reduced key size and improved performance.
Optimizes crypto-oriented neural architectures for faster secure inference.
problem Privacy conflicts between model users and providers in neural network applications.
method Proposes a novel Partial Activation layer to optimize the initial design of crypto-oriented neural architectures.
result Significant improvement in the efficiency of secure inference on common evaluation metrics.
Differential privacy is a statistical concept that can be explained through hypothesis testing.
problem Formalizing differential privacy as a statistical concept.
method Using David Blackwell's informativeness theorem, the paper shows differential privacy can be understood through hypothesis testing.
result The definition of f-differential privacy provides a unified framework for analyzing privacy bounds. We consider the problem of Bayesian learning on sensitive datasets and present two simple but somewhat surprising results that connect Bayesian learning to "differential privacy:, a cryptographic approach to protect individual-level privacy while permiting database-level utility. Specifically, we show that that under s…
This paper applies secure multi-party computation to K-means clustering to protect private data.
problem Privacy-preserving K-means clustering for distributed private data.
method Secure multi-party computation (MPC) techniques to protect private data during K-means clustering.
result Privacy-preserving K-means clustering is feasible and effective for both horizontal and vertical data distribution.
Differential privacy is a cryptographically-motivated definition of privacy which has gained significant attention over the past few years. Differentially private solutions enforce privacy by adding random noise to a function computed over the data, and the challenge in designing such algorithms is to control the added…
Novel algorithm for privacy-preserving distributed learning in analog domain.
problem Privacy-preserving distributed learning over analog data.
method Proposes a novel algorithm for analog data, leveraging real/complex number representation and information-theoretic security metrics.
result Demonstrates a fundamental trade-off between privacy and accuracy in analog domain distributed learning.
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…
Efficiently speeds up privacy-preserving logistic regression.
problem Privacy-preserving machine learning in collaborative studies.
method Customized numerical optimization for secure computing.
result Significant acceleration of logistic regression up to 8.1x.
New framework for privacy-preserving statistical inference using robust statistics.
problem Privacy-preserving statistical inference with robust statistics.
method Introducing a general framework for parametric inference with differential privacy guarantees using M-estimators and test statistics.
result Demonstrated that differential privacy is weaker than robustness and can be achieved by randomizing robust M-estimators.
Hybrid approach protects privacy while analyzing smart meter data.
problem Privacy concerns in AMI data analysis under CPUC regulations.
method Anonymization, differential privacy, federated learning, synthetic data, cryptography.
result Comprehensive privacy-preserving analytics framework for AMI data.
A scalable protocol for federated averaging with privacy and correctness guarantees.
problem Privacy and correctness in federated learning from multiple parties.
method Scalable protocol using correlated and independent Gaussian noise, analyzed for differential privacy and graph topology.
result Nearly matches trusted curator model's utility with minimal communication.
First certified defense scaling to large datasets and models.
problem Robustness against adversarial examples in machine learning models.
method PixelDP, based on differential privacy.
result First certified defense that scales to large networks and models.
PBM mechanism improves privacy and accuracy in federated learning.
problem Secure and private federated learning with limited privacy budget.
method Poisson Binomial mechanism for discrete differential privacy.
result Achieves same privacy-accuracy trade-offs as Gaussian mechanism.
Cryptographic schemes use Thurston norm from 3-manifold topology.
problem Creating secure cryptographic keys.
method Public-key and symmetric-key schemes based on Thurston norm.
result Cryptographic security from 3-manifold topology.
Poisoning datasets can reveal private details of other users' training points.
problem Integrity and privacy of machine learning training data.
method Active inference attacks that poison a small fraction of the training dataset.
result Poisoning as little as 0.1% of the training dataset can significantly boost inference attacks.
Securely evaluates the benefits of merging datasets for causal estimation.
problem Challenges in assessing the value of merging datasets for causal treatment effect estimation.
method Cryptographically secure multi-party computation to evaluate Expected Information Gain (EIG) while ensuring privacy.
result Demonstrates the first privacy-preserving method for dataset acquisition tailored to causal estimation.
Paper addresses federated contextual bandits with encryption.
problem Building contextual bandits with vertically distributed data.
method Design of O3M encryption scheme for LinUCB and LinTS.
result Proposed protocols achieve good performance and privacy.
New adversarial examples from crypto generators show robust machine learning challenges.
problem Adversarial examples in machine learning due to cryptographic pseudo-random generators.
method Constructing a binary classification task with maximal robustness and proving computational hardness under cryptographic assumptions.
result Maximally robust classifiers can tolerate perturbations of size comparable to the examples themselves, highlighting computational hardness.
SOTERIA optimizes neural networks for secure inference with minimal overhead.
problem Protecting user privacy in ML-as-a-service models with low overhead.
method Neural architecture search with dual objectives of accuracy and cryptographic efficiency.
result SOTERIA constructs efficient models for secure inference.
Polynomial-time algorithm estimates mean with bounded covariance using differential privacy.
problem Estimating mean of a d-variate distribution with differential privacy constraints.
method Sum of Squares (SoS) exponential mechanism for polynomial-time differentially private estimation.
result First polynomial-time algorithm with O(d) samples for mean estimation under pure differential privacy. Reduces learning periodic neural networks to lattice problems, proving hardness under cryptographic assumptions.
problem Learning single periodic neurons in noisy environments.
method Reduction to worst-case lattice problems, using LLL algorithm.
result Polynomial-time algorithms for learning these functions are hard under cryptographic assumptions.
Paper tackles efficient HMM learning with conditional samples.
problem Cryptographic hardness in learning HMMs from i.i.d. samples.
method Interactive access model, polynomial-time algorithms for conditional probabilities and latent low rank structures.
result Efficient algorithms for HMM learning in both exact and approximate conditional settings.
PHAZE framework uses zkML and hashing for fast, verifiable LHC trigger decisions.
problem Inefficient inference on large machine learning models for LHC trigger performance.
method Cryptographic techniques like hashing and zkML for low latency, certifiable inference.
result Achieves nanosecond-order latency for LHC triggers, enabling dynamic low-level triggers.
Quantum crypto-economics models price risks in blockchain technology.
problem Quantum technology's potential to undermine blockchain security.
method Building financial models to price quantum risk in blockchain scenarios.
result Quantum crypto-economics models can assess and price quantum risks in blockchain.
Prime Match protects client stock trades from market price manipulation.
problem Protecting client stock trades from market price manipulation.
method Prime Match uses a two-round secure linear comparison protocol to match orders without revealing information.
result Prime Match reduces market impact and maintains client privacy.
Enhances fault tolerance of neural networks for security-critical applications.
problem Fault tolerance of neural networks is biased and can lead to severe consequences in security-critical scenarios.
method Proposes a revised implementation that significantly enhances the fault tolerance property of neural networks with detailed mathematical analysis.
result Significantly increased fault tolerance of neural networks for security-critical applications.
This paper strengthens the computational separation between multimodal and unimodal learning, showing unimodal learning is hard on typical instances.
problem Theoretical justification for empirical success of multimodal machine learning.
method Introduced a stronger average-case computational separation between unimodal and multimodal learning.
result For typical instances, unimodal learning is computationally hard, while multimodal learning is easy.
Hard to estimate L2-accurate scores without strong assumptions.
problem Estimating the score of unknown data distributions accurately.
method Reduction to generating samples and leveraging lattice-based cryptography hardness.
result Score estimation is computationally hard even with polynomial sample complexity.
Local regularization fails in transductive learning for some multiclass problems.
problem Whether local regularization can learn all transductive multiclass problems.
method Provided a negative answer by exhibiting a specific multiclass problem.
result Local regularization cannot learn all transductive multiclass problems.
SANNS secures k-NNS queries and results without revealing them.
problem Securely searching for nearest neighbors without exposing sensitive data.
method Optimized linear scan and clustering-based algorithm with cryptographic primitives.
result SANNS achieves up to 31x faster response times and scales to 10 million entries.
Approach to verify neural network training integrity.
problem Poisoning attacks during neural network training.
method Use of cryptographic mechanisms to verify training integrity.
result Provable verification of neural network training integrity.
Study shows computational hardness can improve adversarial robustness in learning.
problem Developing robust machine learning models against adversarial attacks.
method Investigate if computational limitations of attackers can enhance robustness.
result Demonstrated a learning task where computational robustness outperforms information-theoretic robustness.
Quantum computers outperform classical methods in density modeling.
problem Density modeling with quantum computers.
method Quantum-classical separation for density modeling.
result Quantum computers offer a super-polynomial advantage over classical algorithms for density modeling.
Federated learning platform for drug discovery without sharing data.
problem Lack of secure collaboration in drug discovery.
method Industry-scale federated learning platform using cryptographic aggregation.
result Generated new scientific discoveries in drug discovery.
Boosting algorithm reduces error in noisy data.
problem Improving weak learners in the presence of Massart noise.
method First computationally efficient boosting algorithm for Massart noise.
result Achieves misclassification error arbitrarily close to Massart noise threshold.
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…
Generative adversarial networks improve pseudo-random number generation.
problem Improving the quality of pseudo-random number generators.
method Training a GAN to generate sequences that are hard for an adversary to predict.
result GAN-trained neural networks can produce pseudo-random sequences with good statistical properties.
Safe-House secures DeFi by limiting losses and enhancing security.
problem Ongoing hacks and security concerns in DeFi.
method Safe-House uses blockchain principles to secure asset movements.
result Safe-House limits maximum one-time loss to specified limits.