Securely trains neural networks remotely with deep learning's flaws.
problem Secure and efficient training of neural networks over unsecured channels.
method Leverages deep learning's weaknesses for secure training.
result Efficient and secure training of neural networks remotely.
Securely share encrypted data for machine learning training.
problem Securely sharing encrypted data for machine learning training without revealing the data.
method Rotation based method using flow model.
result Theoretical justification and demonstration of effectiveness in different scenarios.
Securely trains regression models with secret sharing for data collaboration.
problem Balancing data collaboration for technological improvements with security concerns.
method Secret sharing scheme for scalable and efficient secure multiparty training.
result Scalable and efficient protocols for training linear and logistic regression models.
The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the eno…
Paper proposes a secure protocol for federated learning.
problem Combining robustness, privacy, and security in federated learning.
method Secure two-server protocol for federated learning.
result Offers both input privacy and Byzantine-robustness.
Secure aggregation for buffered asynchronous federated learning without TEEs.
problem Privacy and convergence in buffered asynchronous federated learning.
method Developed a new protocol (BASecAgg) that ensures privacy without TEEs by carefully designing masks.
result BASecAgg achieves similar convergence guarantees as FedBuff without TEEs.
Federated learning leaks participant dataset quality even with secure aggregation.
problem Leakage of participant dataset quality in federated learning with secure aggregation.
method Image recognition experiments to infer and attribute dataset quality.
result Relative quality ordering of participants can be inferred and used for various purposes.
New study analyzes security of neural network data reconstruction attacks.
problem Data reconstruction attacks pose a threat to private training data.
method Analyzes security boundary of data reconstruction attacks via neuron exclusivity state.
result Characterizes insecure/secure boundary of data reconstruction attacks.
Secure XGB for privacy-preserving machine learning in federated learning.
problem Privacy-preserving machine learning in federated learning with practical gradient tree boosting models.
method Secure multi-party computation, distributed model storage, secure permutation protocols.
result Our XGB models provide competitive accuracy and practical performance.
Paper analyzes InstaHide's security, recovering all private images with provable guarantee.
problem Protecting privacy of training data in neural networks.
method Unified framework to understand and analyze attacks on InstaHide, presenting a new algorithm to recover all private images with provable guarantee.
result InstaHide is computationally secure but not information-theoretically secure when mixing two private images.
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that can compromise its integrity and efficiency. Security attacks can be divided bas…
Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descen…
PrivacyFL simulates privacy-preserving federated learning.
problem Ensuring privacy in federated learning environments.
method Extensible, configurable simulator for federated learning.
result PrivacyFL checks feasibility and improves model accuracy.
FastSecAgg improves federated learning security and efficiency.
problem Privacy leakage in federated learning due to model parameter sharing.
method Introduces FastSecAgg, a secure aggregation protocol with FFT-based multi-secret sharing (FastShare).
result Efficient in computation and communication, robust to client dropouts.
Secure SMMD enables data privacy in federated learning.
problem Data privacy in federated learning.
method Homomorphic encryption-based Secure Maximum Mean Discrepancy (SMMD).
result Secure SMMD avoids data leakage and enables effective knowledge transfer.
We develop a secure aggregation protocol for federated learning that reduces communication and computation costs.
problem Expensive communication and privacy concerns in federated learning.
method Adapting compression-based federated techniques to additive secret sharing.
result Our protocol achieves high accuracy with low communication costs and is more efficient than prior work.
Proposes a secure communication method independent of eavesdropper's decoder.
problem Lack of practical security constraints in existing methods.
method Dual MINE-based neural secure communications model.
result Security performance is not affected by eavesdropper's decoding means.
COPML framework securely trains models across multiple data owners without revealing individual data.
problem Privacy-preserving collaborative machine learning with multiple data owners.
method Securely encodes data, distributes computation, performs distributed training.
result Achieves up to 16x speedup in training time while maintaining strong privacy.
Deep-Lock secures DNN models with secret keys.
problem Preventing unauthorized usage of DNN models.
method Uses S-Boxes and key scheduling to encrypt DNN parameters.
result Ensures correct functioning only with the correct secret key.
We present \texttt{secml}, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adversarial examples against deep neural networks and training-time poisoning attacks against support vec…
Cloud computing is gaining significant attention, however, security is the biggest hurdle in its wide acceptance. Users of cloud services are under constant fear of data loss, security threats and availability issues. Recently, learning-based methods for security applications are gaining popularity in the literature wi…
LightSecAgg reduces secure aggregation complexity in FL.
problem Complexity in secure aggregation protocols for FL systems.
method One-shot aggregate-mask reconstruction via mask encoding/decoding.
result Significantly reduces overhead for resiliency against dropped users.
Stochastic defense improves natural classifiers against adversarial attacks.
problem Vulnerability of deep networks to adversarial attacks.
method Long-run MCMC sampling with Energy-Based Model for adversarial purification.
result Balancing memoryless and metastable behavior leads to effective purification and robust classification.
A system for federated learning with private data, adding discrete Gaussian noise and secure aggregation.
problem Training models on private data distributed across devices while ensuring privacy.
method Discretizes data, adds discrete Gaussian noise, and uses secure aggregation to protect privacy.
result Matches the accuracy of central differential privacy with less than 16 bits of precision per value.
Proposes a new method to improve deep model security against adversarial deformations.
problem Deep neural networks' resistance to adversarial attacks, especially location perturbations.
method Regularizes flow gradients to provide a tighter bound and improve model resistance.
result Models trained with flow gradient regularization show better resistance to adversarial deformations compared to input gradient regularization and adversarial training.
Federated Learning enables mobile devices to collaboratively learn a shared inference model while keeping all the training data on a user's device, decoupling the ability to do machine learning from the need to store the data in the cloud. Existing work on federated learning with limited communication demonstrates how …
This study extends verifiable learning to boosted tree ensembles, enabling efficient security verification.
problem Efficiently verifying the robustness of boosted tree ensembles against norm-based attackers.
method Formal verification of robustness for large-spread boosted tree ensembles, considering L∞-norm and pseudo-polynomial time for Lp-norm verification. result Polynomial time verification for L∞-norm attackers, NP-hard for other norms, and pseudo-polynomial time for Lp-norm verification. Distributed learning across a coalition of organizations allows the members of the coalition to train and share a model without sharing the data used to optimize this model. In this paper, we propose new secure architectures that guarantee preservation of data privacy, trustworthy sequence of iterative learning and equ…
Distributed Support Vector Machines (DSVM) have been developed to solve large-scale classification problems in networked systems with a large number of sensors and control units. However, the systems become more vulnerable as detection and defense are increasingly difficult and expensive. This work aims to develop secu…
Secure federated learning framework resists adversarial users.
problem Resilience against adversarial (Byzantine) users in federated learning.
method Integrated stochastic quantization, verifiable outlier detection, and secure model aggregation.
result First single-server Byzantine-resilient secure aggregation framework (BREA) for secure federated learning.
The ever-growing big data and emerging artificial intelligence (AI) demand the use of machine learning (ML) and deep learning (DL) methods. Cybersecurity also benefits from ML and DL methods for various types of applications. These methods however are susceptible to security attacks. The adversaries can exploit the tra…
Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications. A commonly used transfer learning approach involves taking a part of a pre-trained model, adding a few layers at the …
Turbo-Aggregate reduces secure aggregation time from quadratic to nearly linear.
problem Quadratic overhead in secure model aggregation for federated learning.
method Multi-group circular strategy, additive secret sharing, and coding techniques.
result Achieves O(NlogN) overhead, compared to O(N2), for up to 50% user dropout. New method protects neural networks from adversarial attacks without generating adversarial examples.
problem Vulnerability of neural networks to adversarial examples.
method Entropic retraining, inspired by information theory.
result Significant increase in NNs' security and robustness.
Securely trains fair models using homomorphic encryption.
problem Protecting sensitive features while testing model fairness.
method Fully homomorphic encryption for training and testing.
result Practical application to adult income data set.
Article evaluates AI security threats and proposes multiple measures.
problem Threats to AI integrity and security.
method Literature review, analysis of AI supply chain, discussion of mitigations.
result Multiple protective measures are necessary for AI security.
Enhances financial time-series prediction by adapting pre-trained models to new data.
problem Adapting pre-trained financial models to new data sets efficiently.
method Augmented Bilinear Network that retains and adjusts pre-trained neural network knowledge.
result Improves prediction performance and reduces model complexity.
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 on InstaHide's security, linking to phase retrieval problem.
problem Security of InstaHide scheme for private dataset sharing.
method Design of a provable algorithm for private vector recovery.
result Private vectors can be recovered using synthetic vectors and public vectors.
Learning in adversarial settings is becoming an important task for application domains where attackers may inject malicious data into the training set to subvert normal operation of data-driven technologies. Feature selection has been widely used in machine learning for security applications to improve generalization a…
Secure sum outperforms homomorphic encryption in collaborative deep learning.
problem Training deep learning models on private data from multiple parties without revealing the data.
method Used a secure sum protocol in conjunction with default secure channels.
result Secure sum protocol provides superior properties in terms of collusion-resistance and runtime.
QFNN-FFD uses quantum computing and FL for secure financial fraud detection.
problem Financial fraud detection in the financial sector.
method Quantum Federated Neural Network (QFNN-FFD) combining QML and FL.
result Achieves precision rates above 95% and robustness against noise.
Paper tackles robustness in adversarial noise with a meta-optimizer.
problem Sensitivity to adversarial noise hinders machine learning deployment.
method Meta-optimizer learns to robustly optimize models using adversarial examples.
result Meta-optimizer transfers adversarial knowledge to new models without generating new examples.
This paper analyzes how training data can be leaked from gradients in neural networks and proposes a metric for measuring model security.
problem Training data leakage from gradients in neural networks for image classification.
method Formulated the problem as an optimisation problem for each layer, involving weights, gradients, and constraints from preceding layers.
result Attributed training data leakage to the architecture of the deep network and proposed a metric for measuring model security.
Theorem ensures superior learning outcomes for authorized learners with quantum label encoding.
problem Ensuring data security for authorized learners in machine learning.
method Quantum label encoding and PAC learning framework.
result Authorized learners achieve superior learning outcomes while eavesdroppers do not.
Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of …
Optimizes a portfolio for an investor preferring accepted securities over a reference security.
problem Investor preference for a set of securities over a reference security with constraints.
method Mean-variance optimization with Sharpe Ratio performance measurement.
result Derives an optimal portfolio that maximizes returns while minimizing risk.
Our work specifies the fundamental cost of using secure aggregation in federated learning.
problem Training a distributed model with differential privacy constraints.
method Characterized the communication cost required for optimal accuracy under differential privacy, achieved by a linear scheme.
result The fundamental communication cost is $ ilde{O}\left( \min(n^2\varepsilon^2, d)
ight)$ bits per client, both sufficient and necessary.