A multi-task network avoids indirect discrimination in insurance pricing.
problem Indirect discrimination in insurance pricing models based on protected characteristics.
method Multi-task neural network architecture trained with partial protected characteristic information.
result Multi-task network produces discrimination-free insurance prices with comparable accuracy to conventional models.
Proposes QNN to protect input privacy in neural networks.
problem Protecting input privacy in neural networks.
method Quaternion-valued neural network (QNN) to hide input information.
result QNN effectively protects input privacy without significant accuracy loss.
Adds layers to NNs to protect them from reverse engineering.
problem Extracting the underlying model of a Neural Network.
method Introducing parasitic layers that approximate a noisy identity mapping with a Convolutional NN.
result The protected NN's predictions remain mostly unchanged while making reverse-engineering more complex.
Proposes a general deep neural network method for digital watermarking.
problem Protecting intellectual content in a massive, IoT-acquired image dataset.
method Train a neural network on an image set and use it to protect distinct test images in bulk.
result Demonstrates the robustness and practicality of the proposed method.
This paper optimizes power grid protection settings to maximize network degradation due to cascading attacks.
problem Cascading attacks on power grids and their undetected nature.
method Constrained Bayesian Optimization applied to transmission line protection settings.
result Even limited misconfiguration of protection settings can cause severe cascading attacks.
The dynamics of protection processes has been a fundamental challenge in systemic risk analysis. The conceptual principle and methodological techniques behind the mechanisms involved [in such dynamics] have been harder to grasp than researchers understood them to be. In this paper, we show how to construct a large vari…
RENNs protect input privacy by rotating d-ary features.
problem Protecting input privacy from intermediate-layer features.
method Rotation-equivariant neural networks using d-ary vectors/tensors.
result RENNs effectively hide input information without degrading output accuracy.
This paper tackles the problem of defending a neural network against adversarial attacks crafted with different norms (in particular ℓ∞ and ℓ2 bounded adversarial examples). It has been observed that defense mechanisms designed to protect against one type of attacks often offer poor performance against…
A recent paper suggests that Deep Neural Networks can be protected from gradient-based adversarial perturbations by driving the network activations into a highly saturated regime. Here we analyse such saturated networks and show that the attacks fail due to numerical limitations in the gradient computations. A simple s…
Algorithm removes backdoor watermarks from neural networks robustly.
problem Protecting neural networks from backdoor attacks.
method Neural network laundering algorithm.
result Effective removal of backdoor watermarks with high test accuracy.
The paper proposes methods to infer from privacy-protected data using simulation-based techniques.
problem Valid statistical inference from privacy-protected data is computationally challenging.
method Simulation-based inference methods, including sequential Monte Carlo and neural conditional density estimators.
result Valid statistical inferences can be made from privacy-protected data.
New mechanism protects neural network weights from privacy attacks during self-supervised learning.
problem Privacy risks during fine-tuning stage of self-supervised learning.
method Proposes a novel differential privacy mechanism using additive logistic noise.
result Reduces membership inference attack accuracy to 50% while maintaining below 5% performance loss.
In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap …
Loss minimization leads to multicalibration for neural networks.
problem Ensuring fairness in predictions across multiple protected groups.
method Minimizing squared loss over neural networks of size n.
result Minimizing loss over neural nets of size n implies multicalibration for most values of n.
This paper uses deep learning to improve network threat detection in finance.
problem Detecting unknown threats in large-scale data applications.
method Uses deep learning for advanced threat detection.
result Improves protective measures in the financial industry.
Exact spectral norm regularization improves neural network generalization.
problem Improving neural network generalization while protecting against noise.
method Exact spectral norm regularization of the Jacobian.
result Improved generalization performance compared to previous methods.
New method learns fair representations by separating out protected attributes.
problem Learning fair representations invariant to protected attributes.
method FD-VAE: disentangles latent space into target, protected, and mutual attributes.
result FD-VAE outperforms previous methods in fairness metrics.
Decor protects decentralized learning models from curious users.
problem Privacy violation in decentralized learning.
method Decor uses correlated Gaussian noises to protect local models in decentralized SGD with differential privacy guarantees.
result Decor matches central DP optimal privacy-utility trade-off for arbitrary connected graphs.
Enhances deep learning models to resist adversarial attacks.
problem Protecting deep learning models from adversarial examples.
method Combines two mechanisms: increased robustness at the cost of accuracy and improved accuracy without robustness guarantee.
result Combining mechanisms provides robustness against adversarial examples while maintaining accuracy.
Paper proposes protecting DNN models with secret key preprocessing.
problem Protecting deep learning models from unauthorized access.
method Block-wise pixel shuffling with secret key for preprocessing.
result Protected models maintain close performance to non-protected models with correct key, but accuracy drops significantly with incorrect key.
Inspired by biophysical principles underlying nonlinear dendritic computation in neural circuits, we develop a scheme to train deep neural networks to make them robust to adversarial attacks. Our scheme generates highly nonlinear, saturated neural networks that achieve state of the art performance on gradient based adv…
As state-of-the-art deep neural networks are deployed at the core of more advanced Al-based products and services, the incentive for copying them (i.e., their intellectual properties) by rival adversaries is expected to increase considerably over time. The best way to extract or steal knowledge from such networks is by…
HarDNN detects and protects CNNs from hardware errors.
problem Hardware errors in CNNs can corrupt inference output.
method Statistical error injection and heuristic vulnerability assessment.
result HarDNN improves CNN resilience with minimal additional computation.
The project intends to model the stability of power system with a deep learning algorithm to the problem, aiming to delay the removal of the fault. The so-called "fail-delay cut-off" refers to the occurrence of N-1 backup protection action on the backbone network of the system, resulting in longer time for the removal …
A new federated learning method protects privacy in mobile crowdsensing.
problem Data and model privacy protection in federated extreme gradient boosting for mobile crowdsensing.
method Secret sharing based federated learning architecture FedXGB.
result FedXGB achieves less than 1% accuracy loss while preserving model privacy.
Data ownership and data protection are increasingly important topics with ethical and legal implications, e.g., with the right to erasure established in the European General Data Protection Regulation (GDPR). In this light, we investigate network embeddings, i.e., the representation of network nodes as low-dimensional …
Paper proposes a new approach to GDPR compliance using data protection analytics.
problem Lack of research on data protection risk management and difficulty in GDPR compliance.
method Quantitative approach to data protection risk-based compliance.
result Improves data protection impact assessments by integrating analytics and expert opinions.
Despite achieving remarkable success in various domains, recent studies have uncovered the vulnerability of deep neural networks to adversarial perturbations, creating concerns on model generalizability and new threats such as prediction-evasive misclassification or stealthy reprogramming. Among different defense propo…
Develops methods to measure and reduce fairness in datasets with limited protected attribute labels.
problem Measuring and reducing fairness in datasets with limited protected attribute labels.
method Proposes methods to estimate fairness metrics and train models to limit fairness violations using probabilistic protected attribute labels.
result Our methods provide tighter bounds on true disparity and effectively reduce fairness violations with lesser fairness-accuracy trade-offs.
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.
Paper proposes a method to encrypt faces while maintaining visual similarity.
problem Protecting personal data from unauthorized face recognition.
method Targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
result TIP-IM provides 95%+ protection success rate against face recognition models.
Study protects federated learning models from eavesdropping attacks.
problem Protecting client models in federated learning from eavesdropping adversaries.
method Theoretical analysis and numerical experiments examining various factors.
result Theoretical and experimental results show the effectiveness of protection methods.
Differential Privacy (DP) provides strong guarantees on the risk of compromising a user's data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases. To address this, we propose element level differential privacy, which extends differ…
Convolutional Neural Networks (CNN) are being actively explored for safety-critical applications such as autonomous vehicles and aerospace, where it is essential to ensure the reliability of inference results in the presence of possible memory faults. Traditional methods such as error correction codes (ECC) and Triple …
Fairness audits fail under missing protected labels, especially at zero access.
problem Understanding the reliability of fairness audits with incomplete protected-label data.
method Introduced a seed-calibrated stress test to separate missingness effects from seed-to-seed movement.
result Missing protected labels do not significantly alter fairness mitigation methods, but they can lead to harmful intersectional outcomes.
Deep reinforcement learning approaches have shown impressive results in a variety of different domains, however, more complex heterogeneous architectures such as world models require the different neural components to be trained separately instead of end-to-end. While a simple genetic algorithm recently showed end-to-e…
New methods ensure fairness in noisy protected groups.
problem Noisy or biased protected group information complicates fairness audits.
method Robust optimization techniques to enforce fairness on true groups.
result Robust approaches achieve better true group fairness guarantees.
Paper protects privacy and fairness in deep learning models.
problem Ensuring fairness in deep learning models while protecting sensitive data.
method Uses differential privacy and Lagrangian duality to design fair predictors.
result Demonstrates improved model performance on prediction tasks.
This work develops secure distributed algorithms for machine learning to protect against data poisoning and network attacks.
problem Vulnerability of distributed machine learning algorithms to cyber threats.
method Game-theoretic framework to capture conflicting goals of a learner and an attacker, iterative distributed algorithm.
result Distributed SVM is prone to fail in different types of attacks, with impact depending on network structure and attack capabilities.
Large-scale datasets play a fundamental role in training deep learning models. However, dataset collection is difficult in domains that involve sensitive information. Collaborative learning techniques provide a privacy-preserving solution, by enabling training over a number of private datasets that are not shared by th…
The paper analyzes how to combine self-protection and self-insurance for risk reduction.
problem Combining self-protection and self-insurance for risk reduction when market insurance is absent.
method The approach uses Value-at-Risk and Tail Value-at-Risk to evaluate residual risk and solves the problem using isoquant geometry based on marginal-balance curves.
result The analysis identifies the conditions under which self-protection and self-insurance behave as substitutes or complements.
Researchers create topologically protected knots in a realizable system.
problem Creating topologically protected vortex knots in experimentally realizable systems.
method Investigated non-Abelian vortices in tetrahedral order in spin-2 Bose--Einstein condensates and bent-core nematic liquid crystals.
result Discovered the first topologically protected knots in an experimentally realizable system.
Framework for fair classification with noisy protected attributes and provable guarantees.
problem Fair classification with noisy protected attributes.
method Optimization framework for linear and linear-fractional fairness constraints, handling multiple non-binary attributes.
result Provably fair classifier with minimal accuracy loss, even with large noise.
We consider the problem of obfuscating sensitive information while preserving utility, and we propose a machine learning approach inspired by the generative adversarial networks paradigm. The idea is to set up two nets: the generator, that tries to produce an optimal obfuscation mechanism to protect the data, and the c…
Fair clustering under the disparate impact doctrine requires that population of each protected group should be approximately equal in every cluster. Previous work investigated a difficult-to-scale pre-processing step for k-center and k-median style algorithms for the special case of this problem when the number of …
Study removes bias from chest X-ray embeddings using orthogonalization.
problem Reduces bias in chest X-ray embeddings due to protected features.
method Orthogonalization technique to remove protected feature effects.
result Orthogonalization removes bias and makes predictions of protected attributes infeasible.
No methods currently exist for making arbitrary neural networks fair. In this work we introduce GRAD, a new and simplified method to producing fair neural networks that can be used for auto-encoding fair representations or directly with predictive networks. It is easy to implement and add to existing architectures, has…
Executing deep neural networks for inference on the server-class or cloud backend based on data generated at the edge of Internet of Things is desirable due primarily to the limited compute power of edge devices and the need to protect the confidentiality of the inference neural networks. However, such a remote inferen…