AI's high performance is linked to its vulnerability due to data geometry.
problem Vulnerability of AI systems to adversarial attacks.
method Simple geometric argument based on high-dimensional data sets.
result High performance and vulnerability are intrinsically coupled.
Adversarial policies beat superhuman Go AI systems.
problem Vulnerability of superhuman AI systems to adversarial attacks.
method Training adversarial policies to trick KataGo into making blunders.
result Adversarial policies achieve >97% win rate against KataGo at superhuman settings.
Article evaluates AI security threats and proposes multiple measures.
problem Threats to AI integrity and security.
method Literature review, analysis of AI supply chain, discussion of mitigations.
result Multiple protective measures are necessary for AI security.
The paper solves optimal bounds for separating data points in high dimensions.
problem Correcting AI errors and analyzing vulnerabilities in high-dimensional data.
method General stochastic separation theorems with optimal probability estimates.
result Explicit and optimal estimates of separation probabilities for important classes of distributions.
This paper uses decolonial theory to improve AI's ethical development.
problem AI's risks to vulnerable peoples and negative impacts of innovation.
method Embedding decolonial critical approach in AI technical practice.
result Developing tactics to align AI with ethical principles.
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.
BadGD identifies gradient descent vulnerabilities through strategic backdoor attacks.
problem Gradient descent vulnerabilities through malicious data manipulation.
method Introduces Max RiskWarp, Max GradWarp, and Max GradDistWarp triggers to exploit gradient descent.
result Demonstrates how malicious triggers can significantly alter loss landscapes and gradient calculations.
AI-GAN generates realistic adversarial examples efficiently.
problem Efficient generation of perceptually realistic adversarial examples.
method A joint training of a generator, discriminator, and attacker.
result Achieves high attack success rates and reduces generation time.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
problem Understanding latent concept encodings in AI models.
method Probabilistic perspective on CAVs, deriving mean and covariance.
result CAVs can be adversarially manipulated, highlighting a vulnerability.
Benchmark evaluates AI-generated financial QA hallucinations, highlighting system vulnerabilities.
problem Ensuring factual accuracy of AI-generated financial QA outputs.
method Developed a benchmark dataset and evaluated six detection methods under clean and noisy conditions.
result LLM-based judges and embedding methods perform best, but degrade under noisy conditions.
Survey of determinism issues in financial AI systems.
problem Vulnerabilities in reproducibility of financial AI systems.
method Literature review and first-party experiments on public financial datasets.
result Proposed a layered evaluation framework linking modality-specific metrics to audit readiness.
New approach extracts AI model representations for steering and monitoring.
problem Understanding and steering AI models' internal knowledge representation.
method Feature learning advances for scalable linear concept representations.
result Concept representations enable steering and monitoring of AI models.
PBC improves AI and dynamical subseasonal forecasts by reducing biases.
problem Subseasonal forecast accuracy drops due to model biases and compounding errors.
method Probabilistic bias correction (PBC) using machine learning to correct historical forecasts.
result PBC doubles AI Forecasting System's subseasonal skill and improves dynamical model skill.
AI detects LDDoS attacks by analyzing TCP connection parameters.
problem Detecting low-rate LDDoS attacks that overwhelm server connections.
method AI algorithms trained on simulated and real-world datasets using TCP flow features.
result Decision trees and k-NN achieved high accuracy in classifying attacks, with low false positives and negatives.
Paper explains AI's vulnerability to small changes and proposes a defense.
problem Adversarial attacks on machine learning systems.
method Information-theoretic approach, drawing on communication theory.
result The proposed defense method detects classifier errors caused by small perturbations.
New attack targets speech-based AI models via stock market data.
problem Vulnerabilities in speech-based AI models using LLMs.
method Backdoor attack using acoustic data poisoning.
result Shows possible vulnerabilities in speech-based transformers.
Study identifies a Strategic Gap in market efficiency due to AI-driven timing and complexity in disclosure.
problem Market inefficiency due to structural influence of disclosure timing and complexity.
method Introduces Autonomous Disclosure Regulator, a multi-node AI framework to audit disclosure complexity and unpredictability.
result Companies use confusing language and unpredictable timing to slow down market learning, creating a 60% Structural Gap.
Prior Networks improve adversarial attack detection by estimating uncertainty.
problem Detecting adversarial attacks in AI systems, especially those designed to evade detection methods.
method Prior Networks estimate predictive uncertainty, outperforming Monte-Carlo dropout ensembles.
result Prior Networks significantly outperform baseline approaches in detecting adversarial attacks.
New AI model optimizes personalized care for elderly residents.
problem Limited care workforce impacts health outcomes and quality of life.
method Bandit algorithms for personalized care planning.
result Improves care quality and health outcomes through personalized care planning.
Foresight Arena benchmarks AI forecasting on real-world markets, isolating predictive edge.
problem Evaluating AI forecasting ability in real-world markets is challenging due to overfitting, centralized trust, and conflated metrics.
method Permissionless, on-chain benchmark using probabilistic forecasts, commit-reveal protocol, and smart contracts.
result Demonstrates the need for 350 predictions to reliably distinguish agents of different skill levels.
New method for model inversion attacks on deep networks.
problem Extracting private information from trained deep learning models.
method Leveraging generative adversarial networks to find realistic class representations.
result Efficiency of model inversion attack within a connected lower-dimensional manifold.
AI learns simplified, unstable structures instead of original ones.
problem Why deep learning is successful and unstable.
method Formal definition and conjecture of false structures.
result Deep learning captures simplified, unstable structures (false structures) instead of original ones.
New benchmarks focus on LLM risk in finance, not just accuracy.
problem Standard benchmarks ignore LLM financial risks, leading to unsafe deployment.
method Three-level agenda: model, workflow, and system stress-testing.
result Hidden weaknesses in LLMs are missed by traditional benchmarks.
RESTA defends LLMs against jailbreaking attacks by adding random noise to embeddings.
problem Vulnerability of LLMs to jailbreaking attacks that generate harmful outputs.
method Adds random noise to embedding vectors and aggregates during token generation.
result RESTA achieves superior robustness versus utility tradeoffs compared to baseline defenses.
Paper exposes vulnerabilities in interpreting machine learning models using adversarial attacks on PD plots.
problem Vulnerability of permutation-based interpretation methods, particularly PD plots, to adversarial attacks.
method Adversarial framework to manipulate black-box models and produce deceptive PD plots.
result It is possible to hide discriminatory behaviors in machine learning models through interpretation tools like PD plots.
NTL protects AI models by restricting their generalization ability to specific domains.
problem Protecting AI models as intellectual property in a secure and robust manner.
method Non-Transferable Learning (NTL) captures exclusive data representation and restricts model generalization ability.
result NTL provides robust resistance to watermark removal and data-centric protection for usage authorization.
The detection of software vulnerabilities (or vulnerabilities for short) is an important problem that has yet to be tackled, as manifested by the many vulnerabilities reported on a daily basis. This calls for machine learning methods for vulnerability detection. Deep learning is attractive for this purpose because it a…
Paper proposes methods to reduce adversarial vulnerability in neural networks.
problem Adversarial vulnerability of deep neural networks in safety-critical applications.
method Defining vulnerability, proposing Vulnerability Suppression (VS) loss, and a Bayesian feature pruning method.
result Improves adversarial robustness and clean example performance with minimal parameter reduction.
Paper presents adversarial method for explaining IDS misclassifications.
problem Limited interpretability of machine learning models in IDSs.
method Adversarial machine learning to generate feature modifications.
result Satisfactory explanations match expert knowledge.
Study data biases to predict algorithmic discrimination, developing a Data Bias Profile.
problem Data biases contribute to algorithmic discrimination, but their impact is understudied.
method Analyzed three common data biases across various datasets and models, developing a Data Bias Profile.
result Combination of proxies and label bias can lead to more significant discrimination than underrepresentation alone.
Each year, thousands of software vulnerabilities are discovered and reported to the public. Unpatched known vulnerabilities are a significant security risk. It is imperative that software vendors quickly provide patches once vulnerabilities are known and users quickly install those patches as soon as they are available…
Optimizes explanations for linear models to enhance trust and interpretability.
problem Lack of well-defined interpretability for linear models and ad hoc approaches.
method Optimization framework using coordinate updates on coefficients.
result Derives a family of interpretability metrics for linear models.
Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs), which are designed by attackers to fool deep learning models. Different from re…
Study shows unequal success of membership inference attacks across different groups.
problem Unequal success of membership inference attacks across different groups.
method Established conditions for preventing MIAs and derived connections to fairness and differential privacy.
result Estimating disparate vulnerability to MIAs can lead to overestimation; suitable attacks and statistical framework provided.
Capsule networks are vulnerable to adversarial attacks, similar to convolutional neural networks.
problem Vulnerability of capsule networks to adversarial attacks.
method Compared capsule networks to convolutional neural networks using various adversarial attacks.
result Capsule networks are vulnerable to adversarial attacks, similar to convolutional neural networks.
The paper addresses model vulnerability to image transformations.
problem Vulnerability of computer vision models to distributional shifts.
method Formulates a combinatorial optimization problem and uses search algorithms to evaluate vulnerability regions. Embeds this idea in a training procedure to define new data augmentation rules.
result Trains more robust models against distributional shifts and image manipulations.
Increasing numbers of software vulnerabilities are discovered every year whether they are reported publicly or discovered internally in proprietary code. These vulnerabilities can pose serious risk of exploit and result in system compromise, information leaks, or denial of service. We leveraged the wealth of C and C++ …
Over the past few years, neural networks were proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions. We show that adversarial vulnerability increases with the gradients of the training objective when viewed as a function of the inputs. Surprisi…
New risk measures assess cryptocurrency market vulnerabilities during financial distress.
problem Capturing systemic risk in cryptocurrency markets during financial distress.
method Introducing Vulnerability Conditional Risk Measures (VCoES) and related measures.
result Validated theoretical insights and demonstrated practical relevance in cryptocurrency market.
Hybrid model prices vulnerable options with stochastic volatility.
problem Pricing options with stochastic volatility and credit risk.
method Closed-form hybrid credit risk model with Heston-Nandi GARCH processes.
result Explicit pricing formula for vulnerable options.
AI stocks hedge against AI singularity's economic impact.
problem AI singularity's displacement of consumption.
method Developed an asset pricing model with incomplete markets.
result AI stocks command a premium due to market incompleteness.
Preschool attendance correlates with lower developmental vulnerabilities in Queensland, Australia.
problem Understanding the relationship between preschool attendance and developmental vulnerabilities in different regions.
method Data Analysis and Machine Learning to identify clusters of socio-demographic variables.
result Identified three clusters with varying socio-demographic variables affecting the relationship between preschool attendance and developmental vulnerabilities.
Study analyzes AI's impact on firms, markets, and workers using large language model data.
problem Understanding AI's effect on firms, markets, and workers.
method Used 380 trillion tokens from 400+ large language models to analyze AI's impact.
result Firms with higher AI exposure earn higher returns, creating an AI premium.
Study on measuring vulnerability of neural network parameters via corruption.
problem Understanding the robustness and generalization of deep neural networks.
method Proposes an indicator to measure parameter robustness via parameter corruption and provides a gradient-based estimation.
result Demonstrates the effectiveness of the proposed indicator and training method in improving parameter robustness and accuracy.
New gossip algorithms improve robustness of rank-based statistics in decentralized systems.
problem Ensuring robustness in decentralized AI and edge intelligence systems, especially in the presence of corrupted or adversarial data.
method Developed asynchronous gossip algorithms for computing rank-based statistics.
result First convergence rate bound for asynchronous gossip-based rank estimation.
New AI stock indices classify firms' AI engagement using 10-K filings.
problem Opaque AI selection criteria in existing ETFs.
method NLP analysis of 10-K filings to classify AI stocks.
result Companies with higher AI engagement have greater positive returns.
AI updates can disrupt human-AI teams; new objective improves compatibility.
problem AI updates can disrupt human-AI team performance.
method Introduce compatibility concept, propose re-training objective.
result Current machine learning algorithms do not produce compatible updates.
The paper analyzes risk spillovers between AI ETFs, AI tokens, and green markets.
problem Risk spillovers among AI ETFs, AI tokens, and green markets.
method R2 decomposition method
result AI ETFs and clean energy act as risk transmitters, while AI tokens and green assets act as receivers.