Jointly learning to localize and repair variable-misuse bugs improves program repair.
problem Variable-misuse bugs in programs.
method Multi-headed pointer networks for joint localization and repair.
result Joint model significantly outperforms an enumerative solution.
AI threatens financial stability through misuse and stealth adoption.
problem Misuse and stealth adoption of AI in financial regulations.
method Analysis of AI's potential risks and criteria for AI suitability.
result AI will likely become widely used by stealth, affecting high-level financial functions.
Paper discusses ethical norms for machine learning to prevent misuse.
problem Harmful misuse of machine learning applications.
method Proposes review parameters for ethical framework.
result Ethical guidelines for sharing sensitive machine learning information.
Study detects anomalies in financial markets using GNN and nonextensive entropy.
problem Detecting anomalies in global financial markets with many correlated assets.
method Used Graph Neural Networks (GNN) with nonextensive entropy to measure uncertainty.
result Anomalies are statistically different for nonextensive entropy parameters before, during, and after a crisis.
Research shows how deepfakes can be used to manipulate accounting systems.
problem The vulnerability of CAATs to adversarial attacks.
method Developed a thread model to camouflage anomalies, used adversarial autoencoder neural networks to learn latent factors, demonstrated misuse of model to generate misleading entries.
result Adversarial autoencoder neural networks can learn and manipulate accounting data to deceive CAATs.
Over the past decades, statisticians and machine-learning researchers have developed literally thousands of new tools for the reduction of high-dimensional data in order to identify the variables most responsible for a particular trait. These tools have applications in a plethora of settings, including data analysis in…
Guidelines for using explainable ML to avoid misuse.
problem Misuse of explainable ML, especially for harmful purposes.
method Proposed guidelines to promote best practices.
result Promote interpretable models and testing methods.
Study identifies diverse health states of opioid users to improve policy.
problem Diverse health states of opioid users lead to ineffective policy interventions.
method Probabilistic topic modeling of medical histories.
result Learned phenotypes predict future opioid use and prescription variability.
VC classes can be robustly learned but only by misusing the learning method.
problem Learning adversarially robust predictors.
method Proves that VC classes are learnable with an improper learning rule.
result VC classes are robustly learnable with improper methods.
MeanFlow training is unstable due to misusing conditional velocity, leading to variance issues.
problem Unstable training of MeanFlow due to variance problems.
method Theoretical analysis and derivation of optimal coefficient in closed form.
result The optimal coefficient in MeanFlow training minimizes variance but not necessarily quality.
Extracts factors from Treasury yields using ML techniques.
problem Understanding factors underlying Treasury yields.
method Nonnegative Matrix Factorization (NMF) and clustering.
result Factors identified through NMF and clustering.
Paper proposes detecting video manipulation using stream descriptors.
problem Misuse of manipulated video content.
method Binary classifiers on multimedia stream descriptors.
result Scalable approach can detect high-quality manipulations.
LogDet estimator improves entropy estimation in neural networks.
problem Inconsistent observations and diversified interpretation in neural networks.
method Proposes LogDet estimator for reliable entropy approximation.
result LogDet estimator overcomes distributional diversity issues.
A new layer learns abstract relations from graph structure using finite-state automata.
problem Learning abstract relations from graph structure for program analysis.
method Relaxing the problem into learning finite-state automata policies on a graph-based POMDP and training these policies using implicit differentiation.
result GFSA layer finds shortcuts in grid-world graphs and reproduces simple static analyses on Python programs.
This review is about the convenience, the benefits, as well as the destructive capacities of money. It deals with various aspects of money creation, with its value, and its appropriation. All sorts of money tend to get corrupted by eventually creating too much of them. In the long run, this renders money worthless and …
This article presents FVA and CVA of a bilateral derivative in a coherent manner, based on recent developments in fair value accounting and ISDA standards. We argue that a derivative liability, after primary risk factors being hedged, resembles in economics an issued variable funding note, and should be priced at the m…
Overrides of credit ratings are important correctives of ratings that are determined by statistical rating models. Financial institutions and banking regulators agree on this because on the one hand errors with ratings of corporates or banks can have fatal consequences for the lending institutions and on the other hand…
Survey on privacy issues in deep learning and proposed solutions.
problem Privacy concerns in deep learning models due to sensitive data.
method Review of existing privacy techniques and gaps in research.
result Identification of test-time inference privacy as a research gap.
Improves visualization of high-dimensional data by correcting misleading artifacts in neighbor embedding methods.
problem Misleading visual artifacts in t-SNE and UMAP due to lack of data-independent manifold learning interpretations.
method LOO-map framework that extends embedding maps to the entire input space, identifying and correcting map discontinuities.
result Developed point-wise diagnostic scores to detect unreliable embedding points and improve hyperparameter selection.
FTX's failure linked to Terra-Luna collapse and Binance's influence.
problem FTX's collapse due to misuse of native token and reliance on leverage.
method Analyzed on-chain data, studied cryptocurrency dependency structures, and examined public trades.
result FTX's downfall was accelerated by Binance's tweets and public reaction.
In this paper, the notion of strongly typed language will be borrowed from the field of computer programming to introduce a calculational framework for linear algebra and tensor calculus for the purpose of detecting errors resulting from inherent misuse of objects and for finding natural formulations of various objects…
Confidential Guardian prevents model abstention from being used to discriminate.
problem Dishonest institutions can exploit machine learning model abstention to unfairly deny services.
method Confidential Guardian uses zero-knowledge proofs to verify model confidence and detect suppression.
result Confidential Guardian effectively prevents the misuse of cautious predictions.
Blockchain helps secure payments between AI agents.
problem Ensuring secure payments between untrusted AI agents.
method Systematized four-stage lifecycle for A2A payments on blockchain.
result Challenges remain in weak intent binding, misuse, and limited accountability.
Models continue to increase their already broad use across industry as well as their sophistication. Worldwide regulation oblige financial institutions to manage and address model risk with the same severity as any other type of risk, which besides defines model risk as the potential for adverse consequences from decis…
New framework improves text watermark detection under imperfect pseudorandomness.
problem Structured dependence in generated text from language models causes Type I error control issues.
method Hierarchical two-layer partition, minimal units, non-asymptotic efficiency measure, minimax hypothesis testing.
result Closed-form optimal rules for watermark detection under imperfect pseudorandomness.
Adaptive testing segments watermarked text from LLMs.
problem Distinguishing LLM-generated text from human-written content.
method Generalized likelihood-based detection method adapted to inverse transform sampling, removing prompt estimation sensitivity.
result Effective and robust method for segmenting watermarked text.
The paper proposes a fair reinforcement learning framework to prevent healthcare disparities.
problem Unfair reinforcement learning policies in healthcare can lead to socioeconomically-disadvantaged subgroups being underprivileged.
method The paper introduces a counterfactual fairness framework and a sequential data preprocessing algorithm to achieve fair sequential decision making.
result The proposed approach greatly enhances fair access to counseling in a digital health dataset designed to reduce opioid misuse.
This paper tests LLMs in finance to assess ethical behavior.
problem Aligning AI with ethical and legal standards in finance.
method Prompted LLMs to simulate CEO behavior, analyzed with logistic regression.
result Significant heterogeneity in LLMs' unethical behavior propensity.
Paper presents attacks on real-time object detection systems.
problem Adversarial attacks on real-time object detection systems.
method Three targeted adversarial Objectness Gradient attacks (TOG).
result Adversarial attacks can cause object-vanishing, object-fabrication, and object-mislabeling.
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.
This work addresses unstable MeanFlow training by optimizing a coefficient in the loss function.
problem Unstable training of MeanFlow models with non-decreasing loss and unbounded gradient variance.
method Established a theory attributing the instability to misuse of the conditional velocity field, derived the optimal coefficient, and showed practical realizations.
result Optimal coefficient yields up to 54% improvement in sample quality and monotone FID trend.
Research creates a taxonomy to bridge AI security and regulatory gaps.
problem Disciplinary disconnect between technical and legal teams in AI risk assessment.
method Developed an AI System Threat Vector Taxonomy with 9 domains and 53 sub-threats.
result Empirically validated and aligned with ISO/IEC 42001 controls and NIST AI RMF functions.
This paper formalizes AI safety using hypothesis testing in GenAI.
problem Ensuring safety of generative AI tools that create realistic content.
method Formalization of computational safety through hypothesis testing and signal processing.
result Demonstrates how AI safety can be assessed quantitatively using mathematical frameworks.
ERP improves drug discovery by balancing molecule generation quality and efficiency.
problem Generating valid and optimal molecules from large language models.
method Entropy-Reinforced Planning (ERP) for Transformer Decoding.
result ERP outperforms current state-of-the-art algorithms by 1-5 percent on SARS-CoV-2 and human cancer cell targets.
Measures faithfulness of LLM explanations to reveal hidden biases and misleading claims.
problem LLM explanations can misrepresent the model's reasoning process, leading to over-trust and misuse.
method Defines faithfulness in terms of concept influence and uses counterfactuals and Bayesian models to estimate it.
result Can quantify and discover interpretable patterns of unfaithfulness in LLM explanations.
This paper introduces f-DPO, a generalized approach to Direct Preference Optimization using diverse divergence constraints.
problem Aligning large language models with human preferences while mitigating safety risks.
method Incorporates diverse divergence constraints to simplify the relationship between reward and optimal policy, eliminating the need for estimating the normalizing constant.
result Optimizes LLMs to align with human preferences more efficiently and under a broader set of divergence constraints.
The study examines the discrepancies between binary forecasts and real-world outcomes, revealing their often misleading nature.
problem The confusion between binary forecasts and real-world payoffs in decision-making and prediction.
method Comparative analysis of binary forecasts, bets, and real-world continuous payoffs under different tail conditions.
result Binary forecasting abilities do not translate to better real-world performance, and vice versa, especially under nonlinearities.
Paper shows how to fool mammogram classifiers with adversarial attacks.
problem Vulnerability of mammographic image classifiers to adversarial attacks.
method Trained model on mamographic images, generated adversarial samples, analyzed similarity.
result Demonstrated successful adversarial attacks on mammographic image classifier.
DAWN dynamically embeds watermarks in neural network predictions to prevent model extraction.
problem Preventing theft of machine learning models through model extraction.
method Dynamic adversarial watermarking at prediction API level.
result DAWN effectively resists two state-of-the-art model extraction attacks.
Paper defines AI-specific loss reconstruction problem and introduces CER framework.
problem Reconstructing AI-generated losses, especially in agentic systems.
method CER framework: C (control boundary), E (evidence reconstruction), R (insurance response).
result Defines AI-specific reconstruction problem and operationalizes it.
Deep learning predicts opioid use disorder risk in patients.
problem Identifying patients at high risk of opioid use disorder.
method Applied LSTM models to analyze electronic health records of opioid users.
result LSTM model outperformed other methods with F1 score of 0.8023 and AUCROC of 0.9369.
MAPPING debiases GNNs for fair node classification with limited leakage.
problem Graph Neural Networks inherit and exacerbate historical discrimination in high-stake domains.
method MAPPING uses distance covariance-based fairness constraints and adversarial debiasing.
result MAPPING achieves better trade-offs between fairness and utility, mitigating privacy risks.
The paper addresses bias in fraud detection models by improving label recovery in payment networks.
problem Systematic bias in chargeback labels in payment networks.
method Formalizes the observation pipeline as a sequential missing-data problem with three stages and a corruption layer. Constructs the Sequential Triply Robust (STR) estimator to correct for all four impairments simultaneously.
result Achieves the semiparametric efficiency bound and provably dominates naive chargeback-based training in mean squared error.
Machine learning papers often fail to distinguish between explanation and speculation.
problem Trending issues in machine learning scholarship.
method Analysis of recent trends in machine learning papers.
result Four patterns of poor scholarship in machine learning papers.
Intrusion detection for computer network systems has been becoming one of the most critical tasks for network administrators today. It has an important role for organizations, governments and our society due to the valuable resources hosted on computer networks. Traditional misuse detection strategies are unable to det…
New attacks show ML models can be compromised even when targeting one concept.
problem Vulnerability of ML models to multi-concept attacks.
method Developed novel multi-concept attack techniques for deep learning.
result Successfully attacked one set of classifiers without impacting others.
A rigorous ML pipeline for binary classification in biomedical studies, focusing on pancreatic cancer.
problem Handling bias in ML models for complex biomedical data.
method Customizable ML analysis pipeline with 9 algorithms, hyperparameter optimization, and thorough evaluation.
result Comparison of ML algorithms to ExSTraCS, highlighting interpretability and bias handling.
Proposes a criterion for selecting relevant auxiliary variables in incomplete data analysis.
problem Selecting useful auxiliary variables for incomplete data analysis.
method Formulates model selection problem, proposes an information criterion based on Kullback-Leibler divergence.
result Proposed information criterion is an asymptotically unbiased estimator of Kullback-Leibler divergence.