Proves bounds on copyright risk for generative models.
problem Generative models risk producing similar content to copyrighted data.
method Defines NAF, proves bounds, and provides learning algorithms.
result Generative models can be made less likely to produce copyrighted content.
New method reduces copyright risks in AI-generated images.
problem Copyright issues in AI-generated images.
method Genericization method using originality estimation and PREGen technique.
result PREGen reduces likelihood of generating copyrighted characters by over half.
Study copyright's impact on creative industries using AI-generated fonts.
problem Estimating supply and demand in creative industries with AI-generated content.
method Neural network embeddings, spatial regression, event-study analyses, structural model of supply and demand.
result Copyright can raise consumer welfare by encouraging product relocation.
Machine learning as a service (MLaaS), and algorithm marketplaces are on a rise. Data holders can easily train complex models on their data using third party provided learning codes. Training accurate ML models requires massive labeled data and advanced learning algorithms. The resulting models are considered as intell…
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.
It is well-known that many machine learning models are susceptible to adversarial attacks, in which an attacker evades a classifier by making small perturbations to inputs. This paper discusses how industrial copyright detection tools, which serve a central role on the web, are susceptible to adversarial attacks. We di…
NegToMe uses images to guide text-based models away from unwanted visual elements.
problem Insufficient text-based adversarial guidance for complex visual concepts.
method Negative token merging (NegToMe) using visual features from reference images.
result Significantly enhances output diversity and reduces visual similarity to copyrighted content.
The paper tackles data misappropriation in LLMs by embedding watermarks and testing for their presence.
problem Detecting data misappropriation in LLMs trained on copyrighted data.
method Embedding watermarks, formulating as hypothesis testing, developing statistical framework, constructing test statistics, determining optimal thresholds, controlling errors, establishing asymptotic optimality.
result The proposed statistical testing framework effectively detects data misappropriation in LLMs.
When machine learning systems fail because of adversarial manipulation, how should society expect the law to respond? Through scenarios grounded in adversarial ML literature, we explore how some aspects of computer crime, copyright, and tort law interface with perturbation, poisoning, model stealing and model inversion…
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.
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.
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.
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.
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.
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.
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.
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.
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.
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 …
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.
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.
Protects user privacy in models using optional personal data.
problem Ensuring fairness for users who opt-out of data sharing.
method Formalizes protection requirements, introduces Protected User Consent (PUC), devises data augmentation strategy.
result PUC-compliant models can improve performance without disadvantaging opt-out users.
ARL improves fairness without protected features, showing AUC improvements for worst-case groups.
problem Training fairness in ML without known protected features.
method Adversarially Reweighted Learning (ARL) using non-protected features and task labels.
result ARL improves Rawlsian Max-Min fairness with notable AUC improvements for worst-case groups.
Proposes a new method for fairness in machine learning with multiple protected attributes.
problem Ensuring fairness in machine learning models with continuous and multiple protected attributes.
method Distance covariance regularisation framework to mitigate association between model predictions and protected attributes.
result Demonstrates effectiveness in mitigating fairness gerrymandering in regression tasks.
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.
New algorithm mitigates bias in subset selection with noisy protected attributes.
problem Mitigating bias in subset selection when protected attributes are noisy.
method Formulated a denoised selection problem and developed a linear-programming based approximation algorithm.
result The approach can produce fairer subsets despite noisy protected attributes.
Topologically protected vortex knots and links are proposed and proven.
problem Decaying of tangled vortex structures through local reconnections and strand crossings.
method Proposed and proven topologically protected vortex structures using non-Abelian topological vortices.
result Existence of topologically protected Q8-colored links and classification using the Q-invariant. New EPS insurance offers partial protection against superannuation losses.
problem Lack of efficient investment insurance for superannuation holders.
method Developed a new financial derivative, equity protection swap (EPS), and derived a fair pricing formula.
result EPS can be an efficient investment insurance tool for superannuation accounts.
Fairness has become a central issue for our research community as classification algorithms are adopted in societally critical domains such as recidivism prediction and loan approval. In this work, we consider the potential bias based on protected attributes (e.g., race and gender), and tackle this problem by learning …
Invariants for colored links found, with topological protection of certain knots.
problem Finding invariants for colored links and understanding their topological stability.
method Equivariant bordism groups of Conner and Floyd, topological surgeries.
result Topological protection of certain tricolored knots, with specific transformations.
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.
New fairness criterion for risk-sensitive decisions in regulated industries.
problem Ensuring equitable outcomes in risk-sensitive decision-making.
method Marginal fairness for generalized distortion risk measures, two-step decision-making process.
result Ensures fairness in decision-making under risk measures, regardless of protected attributes.
This paper examines MEV attacks in dynamic AMMs and proposes new protections.
problem Dynamic AMMs introduce new MEV attack vectors due to inter-block weight changes.
method Analyzed inter-block weight changes as analogous to trades, conducted simulations.
result New inter-block protections are required to guard against multi-block MEV attacks.
Study shows how price protection affects online learning algorithms for dynamic pricing.
problem Impact of price protection guarantee on online learning algorithms for dynamic pricing.
method Characterized the effect of price protection period length on optimal regret, proposed LEAP algorithm.
result Optimal regret is Θ(√T + min{M, T^2/3}) with LEAP matching lower bounds up to logarithmic factors.
Paper presents a dynamic tail risk protection strategy using ML and econometrics.
problem Tail risk protection in finance with solid mathematical and statistical tools.
method Dynamic tail risk protection strategy using weak classifiers (parametric and non-parametric) to estimate exceedance probability and derive trading signals.
result Ensemble classifier improves generalization and trading performance.
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…
Gaussian processes with differential privacy protect both inputs and outputs.
problem Previous DP methods only protected model outputs, not inputs.
method Sparse GP with private variational approximation, adjusting covariance for DP noise.
result Accurate models can be produced under strong privacy protection with sufficient data.
PASS protects private attributes by stochastically substituting data.
problem Protecting private attributes in ML services while maintaining data utility.
method PASS uses stochastic data substitution with a novel loss function derived from information theory.
result PASS effectively protects private attributes across various datasets.
Differential privacy protects data privacy by adding noise to data.
problem Leakage of sensitive data through common methods like encryption and endpoint protection.
method Randomized response technique to add noise to data collection.
result Differential privacy ensures strong privacy with better utility.
Investors target specific regions of payoff distributions for portfolio optimization.
problem Optimizing portfolio performance across different return distribution regions.
method Developed a dynamic portfolio-choice framework targeting downside or upside quantiles.
result Policies focused on downside regions provide stronger left-tail protection and higher Sharpe ratios.
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.
Fawkes protects images from unauthorized facial recognition models.
problem Unauthorized training of facial recognition models poses privacy risks.
method Fawkes adds imperceptible pixel-level changes (cloaks) to images before release.
result Fawkes can protect images from misidentification by 95% and 80% even when clean images are leaked.
SLIP secures LLMs on edge devices by splitting computation and protecting sensitive parts.
problem Protecting LLMs on edge devices from theft and unauthorized use.
method SLIP uses matrix decomposition to split model computation between secure and vulnerable resources, ensuring zero accuracy degradation and minimal latency.
result SLIP is the first practical, secure hybrid protocol for protecting LLMs on edge devices.
There is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race, gender, or age. However, this raises two significant challenges: (1) protected attributes may not be available or it may not be legal to use…
In this paper, we consider a dynamic asset pricing model in an approximate fractional economy to address empirical regularities related to both investor protection and past information. Our newly developed model features not only in terms with a controlling shareholder who diverts a fraction of the output, but also goo…
Vanilla CNNs, as uncalibrated classifiers, suffer from classifying out-of-distribution (OOD) samples nearly as confidently as in-distribution samples. To tackle this challenge, some recent works have demonstrated the gains of leveraging available OOD sets for training end-to-end calibrated CNNs. However, a critical que…
The paper examines how risk reduction and insurance choices interact under convex premium principles.
problem Interaction between self-protection and insurance demand under convex premium principles.
method Investigates optimal prevention efforts and insurance shares using distortion risk measures.
result Self-protection and insurance are complementary, but ex ante moral hazard can turn this into a substitution effect.