Advances fair representation learning for unknown third-party uses.
problem Mitigating unfair prediction outcomes when representations are used by third parties with unknown objectives.
method Adversarial representation learning to ensure fairness.
result Demonstrated fair transfer learning and maintained utility.
Secure neural network inference on untrusted platforms using holographic reduced representations.
problem Secure neural network inference on untrusted platforms.
method Connectionist Symbolic Pseudo Secrets using Holographic Reduced Representations (HRR).
result Empirical robustness to attack under various threat models.
The paper shows supply chain features improve cyber risk prediction.
problem Predicting cyber risk from supply chain attributes.
method Machine learning, external supply chain features, AUC improvement.
result Supply chain network features improve AUC by 2.3%.
New method protects privacy while allowing accurate statistical inference from synthetic data.
problem Ensuring privacy in database release while maintaining statistical utility.
method Kernel mean embedding with differential privacy constraints.
result Consistent estimators of population statistics can be constructed while protecting individual privacy.
We study the problem of portfolio insurance from the point of view of a fund manager, who guarantees to the investor that the portfolio value at maturity will be above a fixed threshold. If, at maturity, the portfolio value is below the guaranteed level, a third party will refund the investor up to the guarantee. In ex…
DADI framework dynamically discovers fair information using reinforcement learning.
problem Discovering fair information from third-party features with unknown objectives.
method Adversarial reinforcement learning agent that balances accuracy and fairness.
result Achieves group fairness by rewarding the agent with the adversary's loss.
A distributed framework protects privacy while maintaining fairness in machine learning.
problem Protecting personal demographic data while ensuring fair machine learning outcomes.
method A distributed framework with private third-party data communication, ensuring privacy and fairness.
result Four fair learning methods consistently outperform existing ones in fairness and accuracy across three real-world datasets.
Lapse-supported life insurance exacerbates adverse selection risks.
problem Lapse-supported life insurance increases adverse selection costs.
method Modeling 'Term to 100' contracts and analyzing three methods of managing lapse surplus.
result Adverse selection losses can be almost unlimited under certain conditions.
New approach to reinforcement learning that balances safety and performance against adversaries.
problem Balancing safety and performance in reinforcement learning against potential adversaries.
method Developed a new reinforcement learning framework that integrates interruptibility, resilience, and safe exploration.
result Achieved both interruptibility and resilience to adversaries without sacrificing optimal policy probability.
We report on a technique based on multi-agent games which has potential use in the prediction of future movements of financial time-series. A third-party game is trained on a black-box time-series, and is then run into the future to extract next-step and multi-step predictions. In addition to the possibility of identif…
Paper proposes a new method to compute cryptocurrency prices securely.
problem Accurate price feeds without a third party.
method Algorithmic method to compute prices from potentially dishonest sources.
result The proposed method can report accurate prices even from dishonest sources.
Wide-AdGraph detects ads and trackers using a graph of resource requests.
problem Detecting and blocking ad trackers to protect user privacy.
method Combining a large-scale graph of resource requests from multiple websites to train a machine learning algorithm.
result High accuracy (96.1% biased, 90.9% unbiased) in detecting ads and trackers.
We show how to restructure the counterparty risk faced by the originator of a securitization or covered bond arising from an interest rate hedging swap assisted by a "one-way" collateral agreement. This risk emerges when the swap is negotiated between the special purpose vehicle and a third party that covers itself thr…
A digital euro protocol offers complete privacy and offline transactions using Groth-Sahai proofs.
problem Fragile digital payment solutions with privacy and offline transaction issues.
method Design and implementation of a Central Bank Digital Currency (CBDC) using Groth-Sahai zero-knowledge proofs.
result Complete privacy and offline transaction capability with retroactive double-spending detection.
Evidence acquisition costs influence disclosure behavior and preference.
problem How evidence acquisition costs affect disclosure behavior and preference.
method Analyzes sender-receiver interactions with covert and overt evidence acquisition, varying certification costs.
result Equilibria converge to the Pareto-worst free-learning equilibrium as costs vanish, and receivers prefer covert to overt acquisition.
Study privacy-utility trade-off in IoT time-series data sharing with RL.
problem Privacy concerns in IoT time-series data sharing with temporal correlations.
method Reformulated as MDP, solved with asynchronous actor-critic deep RL.
result Validated solution on synthetic and real GPS datasets.
This paper assesses risks in DeFi investments.
problem Risks in decentralized finance investments.
method Overview of DeFi components and risk quantification methodology.
result Proposes an allocation methodology to integrate and quantify risks.
Proposes atomic swaptions for trustless cryptocurrency derivatives.
problem Lack of trustless derivatives for cryptocurrency exchanges.
method Extends atomic swap protocol to include derivatives without oracles.
result Atomic swaptions enable trustless exchange of derivative assets.
Federated Learning prioritizes client data contributions for better model quality.
problem Privacy concerns and reluctance to share private data in machine learning.
method Prioritizes client data contributions in Federated Learning by assigning scores based on defined criteria.
result The proposed approach yields a higher quality global model compared to standard Federated Learning.
The paper discusses building ETF risk models using a multilevel classification taxonomy.
problem Building accurate risk models for ETFs.
method First, build a multilevel classification taxonomy for ETFs. Then, use this taxonomy to define risk factors and build risk models.
result The approach can accurately classify and model ETF risks.
We study how to communicate findings of Bayesian inference to third parties, while preserving the strong guarantee of differential privacy. Our main contributions are four different algorithms for private Bayesian inference on proba-bilistic graphical models. These include two mechanisms for adding noise to the Bayesia…
Paper finds a method to compute fair risk-sharing rules.
problem Finding a fair and understandable risk-sharing rule.
method Established a one-to-one correspondence with a fixed point approach.
result Fast numerical method for computing AFPO risk-sharing rules.
Orpheus simplifies deep learning deployment on edge devices.
problem Optimizing deep learning inference on edge devices for efficiency.
method Orpheus is a new framework with a small codebase, minimal dependencies, and easy integration.
result Preliminary results show the effectiveness of Orpheus for inference optimisations.
Study adversarial perturbations in classification, analyzing learning and certification.
problem Formal study of classification under adversarial perturbations from both learner and third-party perspectives.
method PAC-type semi-supervised learning framework, black-box certification under limited query budget, adversary analysis.
result Existence of a polynomial query complexity adversary implies the existence of a sample efficient robust learner.
A framework assesses the quality of crowdsourced weather data.
problem Quality control and assessment of crowdsourced weather data from third-party stations.
method Proposes a simple, scalable, and interpretable AI/Stats/ML framework to assess TPAWS data.
result Demonstrates the performance of the framework using synthetic and real data.
CheckNet verifies neural network inference on untrusted devices.
problem Ensuring secure and tamper-proof inference on untrusted devices.
method A checksum-based approach for neural network inference verification.
result Excellent attack detection and success bounds on various models.
Machine learning improves risk prediction for online lending.
problem Traditional credit scoring models fail to utilize big data effectively.
method Collected diverse data, built and tested ensemble machine learning models (random forest and XGBoost).
result XGBoost model outperforms traditional models in loan default probability prediction.
CoNDA improves domain classification for IPDAs by incorporating new and personalized domains.
problem Continuous learning for new and personalized domains in IPDAs.
method Neural network based approach for incremental learning.
result CoNDA achieves high accuracy and outperforms baselines.
Paper proposes a fast method for approximate data deletion in generative models.
problem Efficient data deletion in unsupervised learning models is an open problem.
method Density-ratio-based framework for generative models, fast method for approximate data deletion, statistical test.
result Theoretical guarantees and empirical demonstrations of the proposed methods across various generative models.
Unlike other industries in which intellectual property is patentable, the financial industry relies on trade secrecy to protect its business processes and methods, which can obscure critical financial risk exposures from regulators and the public. We develop methods for sharing and aggregating such risk exposures that …
Interpool solves interoperability issues by minting, exchanging, and burning tokens within a single liquidity pool.
problem Lack of proper interoperability in blockchain use cases.
method Interpool operates as a standalone liquidity pool that mints, exchanges, and burns tokens, optimizing the order of transactions in the mempool.
result Interpool transforms front-running issues into a solution that ensures ultimate liquidity through a burning procedure, enabling trustless design.
SAPAG attacks distributed learning by reconstructing true training data from gradients.
problem Privacy attacks on distributed learning systems through gradients.
method SAPAG uses a Gaussian kernel-based gradient difference distance measure.
result SAPAG can reconstruct training data on various DNNs and at different training phases.
The paper tackles fair representation learning by smoothing feature mappings.
problem Legal liability for discriminatory use of data by organizations.
method Mapping features to a fair representation space, certifying fairness through chi-squared mutual information.
result Smoothing representation distribution provides generalization guarantees of fairness and maintains accuracy for downstream tasks.
This paper optimizes SMPC for neural network inference, reducing memory and time.
problem Memory and time constraints in secure neural network inference.
method Implemented ABY2.0 protocol, optimized memory usage, and used a helper node.
result MNIST inference reduced from 8.03 GB RAM and 200s to 0.2 GB RAM and 32s.
This study analyzes the alignment between charter value and supervision in banks.
problem The alignment between charter value and supervision in banks is complex and varies by risk type.
method Classification and regression tree analysis using the CAMELS rating system.
result Supervision and charter value are aligned for some types of risk.
The paper examines how decentralized credit curators have taken over risk management from traditional protocols.
problem Risk management in decentralized credit has shifted from centralized protocols to decentralized curators.
method Analysis of ERC 4626 vaults and third-party curators, focusing on capital utilization, concentration, and fee margins.
result Curators have a significant impact on the risk profile of decentralized credit systems, with a small set of curators handling a disproportionate share of system TVL.
Android and Facebook provide third-party applications with access to users' private data and the ability to perform potentially sensitive operations (e.g., post to a user's wall or place phone calls). As a security measure, these platforms restrict applications' privileges with permission systems: users must approve th…
Estimates conversion probabilities from click sequences with privacy constraints.
problem Training models in advertising with limited direct click-conversion links.
method Formalizes learning from attribution sets, constructs unbiased estimator, applies Empirical Risk Minimization.
result Empirical Risk Minimization achieves generalization guarantees and robustness against prior errors.
REDS improves scenario discovery from few simulations, reducing costs by 50-75%.
problem Discovering scenarios in data spaces resulting from simulations with limited computational resources.
method Uses an intermediate machine learning model to label data for subgroup discovery methods.
result Reduces the number of simulations required by 50-75% on average.
AI platforms disrupt investment by personalizing deal sourcing and insights.
problem Lack of scalable, personalized, and privacy-compliant deal sourcing and insights solutions.
method Development of in-house AI platforms that interact directly with funds and learn from interactions.
result AI platforms provide smarter, personalized use cases for funds, offering a competitive advantage.
Method estimates joint distribution of bivariate outcomes.
problem Modeling dependence between bivariate outcomes.
method Semiparametric distribution regression.
result Method performs similarly or better than alternatives in finite samples.
New algorithms improve signal processing in federated learning.
problem Efficiently process distributed signal samples with privacy and communication constraints.
method Proposes overpredictive signal approximations using convex optimization.
result Quantifies tradeoffs between communication cost, sampling rate, and approximation error.
Robust CLIP improves vision models' resistance to attacks.
problem Vulnerability of vision models to adversarial attacks.
method Unsupervised adversarial fine-tuning of CLIP.
result Robust CLIP prevents stealth attacks on vision models.
Paper introduces HISA for efficient FHE computations.
problem Efficiently evaluating encrypted neural networks.
method Developed HISA for FHE applications, including compiler and runtime.
result Generated code is faster than hand-optimized implementations.
Generative adversarial networks create synthetic insurance datasets from confidential originals.
problem Difficulty in accessing or sharing confidential insurance datasets for research.
method Design and use of three GAN architectures tailored for multi-categorical insurance data.
result MC-WGAN-GP synthesizes the best data, CTGAN is easiest to use, and MNCDP-GAN ensures differential privacy.
DFL framework improves action and outcome fairness in policy learning.
problem Fairness in policy learning, especially action and outcome fairness.
method Integrates action and outcome fairness into a multi-objective optimization problem using a lexicographic weighted Tchebyshev method.
result DFL framework improves both action and outcome fairness with minimal value reduction.
A new protocol for private averaging protects data privacy in a crowd of users.
problem Protecting privacy in a crowd of users sharing personal data.
method Massively distributed algorithm for private averaging with malicious adversaries.
result Privacy is preserved even with malicious users, and the algorithm can find arbitrary accuracy solutions.
Paper presents membership encoding for deep learning models to protect training data.
problem Protecting training data from inference attacks and ensuring copyright.
method Membership encoding algorithm for deep neural networks.
result Membership information can be encoded for a subset of training data, robust to model compression and fine-tuning.