Paper develops image disguising to protect privacy in outsourced deep learning.
problem Privacy concerns in outsourced deep learning, especially re-identification and model-based attacks.
method Develops image disguising approach to protect against attacks.
result Image-disguising mechanisms provide high protection against attacks while maintaining model quality.
New algorithms use outsourced data to improve model training efficiency.
problem Limited computational resources restrict model training efficiency.
method Simulation-based algorithms using outsourced data to find good initial points.
result The algorithms can find good initial points with high probability under suitable conditions.
We deal with the problem of outsourcing the debt for a big investment, according two situations: either the firm outsources both the investment (and the associated debt) and the exploitation to a private consortium, or the firm supports the debt and the investment but outsources the exploitation. We prove the existence…
First private Bayesian optimization algorithm with provable performance.
problem Privacy-preserving Bayesian optimization in outsourced settings.
method Random projection-based transformation to preserve privacy and distances.
result Regret bound similar to non-private GP-UCB established for PO-GP-UCB.
Detects backdoors in outsourced models by replicating training steps across multiple servers.
problem Detecting backdoors in models trained on cloud providers without prior knowledge.
method Replicate training steps across multiple servers to identify deviations and malicious updates.
result 99.6% accuracy in identifying backdoored models out of 50% malicious providers.
The paper provides an algorithm for the risk estimation when a company selects an outsourcing service provider for innovation product. Calculations are based on expert surveys conducted among customers and among providers of outsourcing. The surveys assessed the degree of materiality of species at risk.
The paper offers algorithms for managing freelancers and in-house workers in online labor markets.
problem Managing freelancers and in-house workers in online labor markets efficiently.
method Developed algorithms for team formation with outsourcing in an online setting.
result Efficient online algorithms for minimizing costs in hiring and outsourcing.
As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which use hardware and software protections to isolate sensitive computations from the…
Stealthy hardware Trojan exploits DLA architecture vulnerabilities.
problem Security of DLA deployed on hardware accelerators.
method Input Interception Attack (IIA) exploiting statistical properties of DLA outputs.
result Stealthy Trojan can trigger with some definiteness.
Improves distributed SGD convergence speed with reduced computation load.
problem Mitigating stragglers in distributed SGD to speed up convergence.
method Modeling communication and computation times, adapting number of workers and computation load dynamically.
result Significantly reduces computation load while improving convergence speed.
This paper advances theory on the process of collaboration between entities and its implications on the quality of services, information, and/or products (SIPs) that the collaborating entities provide to each other. It investigates the scenario of outsourced IS projects (such as custom software development) where the e…
A deep learning method for regression without model assumptions.
problem Regression prediction without model specification.
method Deep Neural Network (DNN) for point and interval prediction.
result The method outperforms other DNN-based alternatives in stability and accuracy.
P3GM improves privacy-preserving data synthesis for high-dimensional data.
problem Mitigating privacy risks in releasing large volumes of sensitive data.
method Privacy-preserving phased generative model (P3GM) with two-phase learning process.
result P3GM significantly outperforms existing solutions in terms of noise reduction and data accuracy.
Proposes efficient 4PC framework for privacy-preserving machine learning.
problem Need for privacy-preserving machine learning in healthcare and finance.
method Proposes an actively secure 4PC protocol and a framework for PPML.
result Framework operates efficiently and outperforms existing methods.
Novel deep learning approach for fast, differentiable fluid simulations.
problem Challenges in solving incompressible fluid dynamics equations efficiently.
method Physics-constrained training approach for convolutional neural networks.
result Trained models can handle various fluid phenomena and offer fast simulations.
NIFTy.re accelerates imaging models and expands Gaussian processes and variational inference.
problem Slow performance and limited inference strategies in NIFTy.
method Rewritten NIFTy with new modeling principles, inference strategies, and JAX integration.
result Dramatic acceleration of models and new inference capabilities.
In this paper, we consider a privacy preserving encoding framework for identification applications covering biometrics, physical object security and the Internet of Things (IoT). The proposed framework is based on a sparsifying transform, which consists of a trained linear map, an element-wise nonlinearity, and privacy…
Quantum machine learning for 2D classification tasks using optimized feature maps.
problem Classifying data points in finite feature space with quantum machine learning.
method Optimized quantum feature maps and classical model training.
result Exponentially better scaling of deployed kernels in qubit number.
DeepPeep attacks DNN architectures to reveal design details, posing IP theft risks.
problem Protecting DNN architecture from IP theft in cloud-based services.
method Two-stage attack methodology exploiting design characteristics.
result DeepPeep successfully reverses-engineers compact DNN architectures.
Publicly pretraining models on Web data may undermine differential privacy.
problem The use of large Web-scraped datasets in differential privacy models.
method Critical review of leveraging pretrained models on public datasets for differential privacy.
result Publicizing pretrained models as 'private' could harm trust and generalize poorly.
A framework for partially encrypted machine learning using functional encryption.
problem Performing machine learning on encrypted data without revealing sensitive information.
method Combining adversarial training and functional encryption to efficiently compute quadratic functions and prevent feature leakage.
result The proposed framework maintains high model accuracy while significantly improving data privacy.
Paper tackles regression under human assistance, showing NP-hardness and developing a greedy algorithm.
problem Optimizing machine learning models under human intervention.
method Introduced ridge regression under human assistance, derived NP-hardness, and developed a greedy algorithm.
result Greedy algorithm achieves good performance in medical diagnosis and content moderation applications.
In crowd labeling, a large amount of unlabeled data instances are outsourced to a crowd of workers. Workers will be paid for each label they provide, but the labeling requester usually has only a limited amount of the budget. Since data instances have different levels of labeling difficulty and workers have different r…
Machine learning services pose privacy risks if data or model parameters are compromised.
problem Privacy risks in machine learning services when data or model parameters are exposed.
method Systematic review of privacy challenges, adversarial models, attacks, and defenses.
result Need for better evaluations, targeted defenses, and policy studies.
Method reformulates constrained optimization as latent space inference.
problem Optimizing black-box functions with hard constraints.
method Posterior inference in latent space using flow-based models and diffusion models.
result Method achieves superior performance across various tasks.
Study examines European banks' digital transformation strategies.
problem Lack of a common framework for open banking innovation in banking sector.
method Qualitative analysis of partnerships and API development.
result European banks are diversifying and boosting customer relationship management.
Study fair team formation in online labor marketplaces.
problem Design fair algorithms for team formation in online labor marketplaces.
method Define and analyze the Fair Team Formation problem, provide inapproximability results, and develop four algorithms.
result Developed four algorithms for fair team formation in online labor marketplaces.
Train a lightweight carry-on model on existing LLMs for faster customization.
problem Customizing large language models for specific tasks is computationally expensive.
method Train an additional branch of transformer blocks on the final-layer embedding of pretrained LLMs, then merge them with a carry-on module.
result Training a 100M carry-on layer requires less than 1GB GPU memory, making it scalable and affordable.
Improves deep learning robustness by considering task and model.
problem Adversarial attacks on deep learning systems.
method Binary and interval label encoding strategy to redefine classification tasks and design corresponding loss functions.
result Our method enhances robustness without sacrificing accuracy.
The paper proposes geometrizing deep networks to improve deep learning system interpretability.
problem Improving the interpretability of deep learning systems.
method Proposes geometrization of deep networks as a solution.
result Geometrization of deep networks can help understand existing deep learning systems and solve interpretability issues.
Paper interprets deep learning using decision trees and Haar wavelets.
problem Understanding the function approximation capabilities of ReLU deep learning.
method Constructing a deep learning structure equivalent to a forest and approximating Haar wavelet functions with ReLU deep learning.
result ReLU deep learning can be considered as decision trees and approximates Haar wavelet functions with arbitrary precision.
Deep learning models can discriminate against certain groups, requiring computational methods to ensure fairness.
problem Algorithmic discrimination in deep learning models affecting protected groups.
method Interpretability and mitigation approaches at different stages of deep learning lifecycle.
result Interpretability aids in diagnosing and mitigating algorithmic discrimination in deep learning.
Deep RL combines deep learning and RL for complex decision-making.
problem Complex decision-making tasks that were previously unsolvable by machines.
method Combining deep learning and reinforcement learning.
result Deep RL can solve complex tasks and has practical applications.
Probabilistic deep learning uses neural networks and models to handle uncertainty.
problem Handling uncertainty in deep learning models.
method Two approaches: probabilistic neural networks and deep probabilistic models.
result TensorFlow Probability library supports both approaches.
Integrates deep learning and logic reasoning for intelligent agents.
problem Combining deep learning and logic reasoning for robust decision-making.
method Deep Logic Models integrating deep learners and logic reasoning.
result Proposed models outperform other approaches in joint learning and inference.
The great success of deep learning shows that its technology contains profound truth, and understanding its internal mechanism not only has important implications for the development of its technology and effective application in various fields, but also provides meaningful insights into the understanding of human brai…
Deep learning brings major advances in AI, especially in computer vision.
problem Keeping track of regular advances in deep learning is challenging for new researchers.
method Briefly discusses recent advances in deep learning over the past few years.
result Revolutionary advances in computer vision and machine learning.
Deep learning improves crime prediction accuracy.
problem Improving crime prediction accuracy using deep learning.
method Comparative study of 10 deep learning methods on crime data.
result Deep learning methods outperform existing methods in crime prediction.
This paper provides an overview of deep semi-supervised learning methods.
problem Reducing the need for large annotated datasets in deep learning.
method Summarizes dominant semi-supervised approaches in deep learning.
result Provides a comprehensive overview of deep semi-supervised learning.
NeurIPS 2020 competition seeks to predict deep learning generalization.
problem Understanding and predicting generalization in deep learning models.
method Propose complexity measures to accurately predict generalization performance.
result A robust complexity measure could improve deep learning reliability.
Enhances deep reinforcement learning with object recognition.
problem Few works consider object characteristics in deep reinforcement learning.
method Proposes a novel method to incorporate object recognition into deep reinforcement learning models.
result Shows state-of-the-art results on Atari games.
This paper analyzes generalization issues in deep reinforcement learning.
problem Understanding and improving generalization capabilities of deep reinforcement learning policies.
method Formalizing and categorizing solutions to address overfitting in deep reinforcement learning.
result A comprehensive analysis of generalization challenges and solutions in deep reinforcement learning.
Proposes a new Deep Recurrent Double Q-Learning model for Atari games.
problem Improving Deep Reinforcement Learning models for Atari games.
method Integrates Double Q-Learning and Recurrent Networks (LSTM, DRQN) for Atari games.
result Demonstrates improved performance in Atari games compared to existing models.
Deep learning is viewed differently by various disciplines.
problem Understanding deep learning across different fields.
method Synthesizing perspectives from neuroscience, physics, math, and computation.
result Different disciplines offer unique insights into deep learning.
Deep-RLS uses deep learning to improve PCA for better source separation.
problem Improving PCA for better source separation in nonlinear systems.
method Inspired by RLS, Deep-RLS unfolds RLS iterations into a deep neural network.
result Deep-RLS significantly improves accuracy in recovering source signals.
Deep learning improves retinal fundus image analysis for eye diseases.
problem Improving accuracy in diagnosing eye diseases using retinal images.
method Review of deep learning models and datasets for retinal image analysis.
result Deep learning enhances detection and classification of eye diseases.
Deep active inference learns policies from sensory inputs.
problem Learning policies in partially observable domains.
method Optimizes expected free energy with a variational autoencoder.
result Comparable or better performance than deep Q-learning.
Deep learning uses complex networks for high-dimensional data.
problem Computational inefficiency in training deep learning models.
method Use of hierarchical latent variables, efficient linear algebra, SGD optimization, and batch sampling.
result Efficient training and inference possible with optimized algorithms.