A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Framework for fair classification with noisy protected attributes and provable guarantees.
Paper introduces SPADE method to protect classifiers from OOD and adversarial samples.
CST detects discrimination by comparing protected and non-protected individuals with a counterfactual.
Topologically protected vortex knots and links are proposed and proven.
Paper presents a dynamic tail risk protection strategy using ML and econometrics.
Machine learning (ML) classification is increasingly used in safety-critical systems. Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is that of an attacker perturbing a confidently classified input to produce a confident misclassification. To protect against this we devi…
A popular methodology for building binary decision-making classifiers in the presence of imperfect information is to first construct a non-binary "scoring" classifier that is calibrated over all protected groups, and then to post-process this score to obtain a binary decision. We study the feasibility of achieving vari…
New framework for fair classification in adversarial settings with provable guarantees.
Optimizes signal detection in particle physics by decorrelating classifiers.
TaCo prevents non-linear classifiers from detecting sensitive attributes.
New attacks show ML models can be compromised even when targeting one concept.
Most approaches aiming to ensure a model's fairness with respect to a protected attribute (such as gender or race) assume to know the true value of the attribute for every data point. In this paper, we ask to what extent fairness interventions can be effective even when only imperfect information about the protected at…
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…
Study removes bias from chest X-ray embeddings using orthogonalization.
Deep chest X-ray classifiers show bias in predicting diagnoses.
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…
Validates neural networks inputs to protect against adversarial examples.
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…
Differentially private ensemble classifiers adapt to data streams while protecting privacy.
Classifiers and rating scores are prone to implicitly codifying biases, which may be present in the training data, against protected classes (i.e., age, gender, or race). So it is important to understand how to design classifiers and scores that prevent discrimination in predictions. This paper develops computationally…
Develops methods for fair classification under linear disparity constraints.
A new framework reduces data upload for image classification while protecting user privacy.
We consider the task of training classifiers without labels. We propose a weakly supervised method---adversarial label learning---that trains classifiers to perform well against an adversary that chooses labels for training data. The weak supervision constrains what labels the adversary can choose. The method therefore…
As AI systems develop in complexity it is becoming increasingly hard to ensure non-discrimination on the basis of protected attributes such as gender, age, and race. Many recent methods have been developed for dealing with this issue as long as the protected attribute is explicitly available for the algorithm. We addre…
This paper tackles fair Bayes-optimal classifiers under predictive parity, proving their limitations and proposing a new algorithm.
We present FlipTest, a black-box technique for uncovering discrimination in classifiers. FlipTest is motivated by the intuitive question: had an individual been of a different protected status, would the model have treated them differently? Rather than relying on causal information to answer this question, FlipTest lev…
SEP uses checkpoints to protect data from training good models.
Machine learning is becoming an ever present part in our lives as many decisions, e.g. to lend a credit, are no longer made by humans but by machine learning algorithms. However those decisions are often unfair and discriminating individuals belonging to protected groups based on race or gender. With the recent General…
Privacy-preserving boosting algorithm for machine learning.
New methods detect unfairness in multiclass classifiers using DCP.
Real-world applications of machine learning tools in high-stakes domains are often regulated to be fair, in the sense that the predicted target should satisfy some quantitative notion of parity with respect to a protected attribute. However, the exact tradeoff between fairness and accuracy is not entirely clear, even f…
The widespread use of ML-based decision making in domains with high societal impact such as recidivism, job hiring and loan credit has raised a lot of concerns regarding potential discrimination. In particular, in certain cases it has been observed that ML algorithms can provide different decisions based on sensitive a…
privGAN protects synthetic data from membership inference attacks.
Paper proposes protecting DNN models with secret key preprocessing.
We consider the problem of a neural network being requested to classify images (or other inputs) without making implicit use of a "protected concept", that is a concept that should not play any role in the decision of the network. Typically these concepts include information such as gender or race, or other contextual …
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…
New classifiers ensure fairness by adjusting a base classifier's operating characteristics.
Paper proposes a new approach to GDPR compliance using data protection analytics.
We formulate a family of spin Topological Quantum Filed Theories (spin-TQFTs) as fermionic generalization of bosonic Dijkgraaf-Witten TQFTs. They are obtained by gauging -equivariant invertible spin-TQFTs, or, in physics language, gauging the interacting fermionic Symmetry Protected Topological states (SPTs) with a …
Motivated by settings in which predictive models may be required to be non-discriminatory with respect to certain attributes (such as race), but even collecting the sensitive attribute may be forbidden or restricted, we initiate the study of fair learning under the constraint of differential privacy. We design two lear…
Develops methods to measure and reduce fairness in datasets with limited protected attribute labels.
A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information (e.g., gender or ethnic group) as part of a statistical model, and any commitment to protect these characteristics. Often, due to biases pre…
Image classifiers often suffer from adversarial examples, which are generated by strategically adding a small amount of noise to input images to trick classifiers into misclassification. Over the years, many defense mechanisms have been proposed, and different researchers have made seemingly contradictory claims on the…
Study protects federated learning models from eavesdropping attacks.
Fairness audits fail under missing protected labels, especially at zero access.
This paper proposes a use of an ordinal classifier to evaluate the financial solidity of non-life insurance companies as strong, moderate, weak, and insolvency. This study constructed an efficient classification model that can be used by regulators to evaluate the financial solidity and to determine the priority of fur…
New methods ensure fairness in noisy protected groups.
The paper analyzes how to combine self-protection and self-insurance for risk reduction.