Industry lacks tools to secure ML systems, study finds.
problem Insufficient security tools for ML systems in industry.
method Interviews with 28 organizations to identify gaps.
result Need revised Security Development Lifecycle for ML.
On-device research index
arXiv research
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.
168,786 papers · 148 categories
Trend · papers per month
48 results for “ML security”
Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inferencecs.LG
The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the eno…
The DoD needs a robust process to evaluate AI/ML model performance and robustness.
problem AI/ML models are brittle and nonrobust, posing risks in national security.
method Reviews AI/ML development process and best practices for evaluation.
result Recommendations for DoD evaluators to ensure robust AI/ML capabilities.
Survey on securing ML for healthcare, addressing privacy and robustness issues.
problem Security and robustness challenges in healthcare ML/DL applications.
method Overview of security and privacy methods for ML in healthcare.
result Discussion of current research challenges and future directions.
Survey examines ML for IoT security, addressing new challenges.
problem IoT security challenges due to rapid growth and diverse attacks.
method Comprehensive literature review of ML-based security solutions.
result ML provides dynamic and efficient security for IoT.
The future Internet of Things (IoT) will have a deep economical, commercial and social impact on our lives. The participating nodes in IoT networks are usually resource-constrained, which makes them luring targets for cyber attacks. In this regard, extensive efforts have been made to address the security and privacy is…
Explores security challenges of machine learning in real-world systems.
problem Vulnerabilities in machine learning models deployed in safety-critical systems.
method Broadens systems security view of ML vulnerabilities, identifies novel challenges, proposes mitigation suggestions.
result Highlights novel challenges and proposes mitigation strategies for securing ML systems.
The ever-growing big data and emerging artificial intelligence (AI) demand the use of machine learning (ML) and deep learning (DL) methods. Cybersecurity also benefits from ML and DL methods for various types of applications. These methods however are susceptible to security attacks. The adversaries can exploit the tra…
SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measurecs.LG
SafeML monitors ML systems for safety and security risks.
problem Ensuring safety and explainability of ML systems in safety-critical domains.
method Statistical difference measures of ECDF to detect distributional shifts.
result Approach can detect invalid application contexts of ML components.
Connected and autonomous vehicles (CAVs) will form the backbone of future next-generation intelligent transportation systems (ITS) providing travel comfort, road safety, along with a number of value-added services. Such a transformation---which will be fuelled by concomitant advances in technologies for machine learnin…
There has been a surge of interest in using machine learning (ML) to automatically detect malware through their dynamic behaviors. These approaches have achieved significant improvement in detection rates and lower false positive rates at large scale compared with traditional malware analysis methods. ML in threat dete…
Adversarial attacks can manipulate ML-aided visualizations, tricking analysts.
problem Adversarial attacks on ML-aided visualizations.
method Identifying attack surface and exemplifying five adversarial attacks.
result Adversaries can induce various attacks, like creating arbitrary and deceptive visualizations.
Bayesian methods improve adversarial machine learning robustness.
problem Improving machine learning systems' security against adversarial manipulation.
method Integrating Bayesian perspectives to relax unrealistic assumptions in game-theoretic models.
result Bayesian approach provides more robust inferences about opponent's beliefs and interests.
Statistical learning is the process of estimating an unknown probabilistic input-output relationship of a system using a limited number of observations. A statistical learning machine (SLM) is the algorithm, function, model, or rule, that learns such a process; and machine learning (ML) is the conventional name of this…
Machine learning (ML) started to become widely deployed in cyber security settings for shortening the detection cycle of cyber attacks. To date, most ML-based systems are either proprietary or make specific choices of feature representations and machine learning models. The success of these techniques is difficult to a…
Privacy concern has been increasingly important in many machine learning (ML) problems. We study empirical risk minimization (ERM) problems under secure multi-party computation (MPC) frameworks. Main technical tools for MPC have been developed based on cryptography. One of limitations in current cryptographically priva…
Federated Learning is the current state of the art in supporting secure multi-party machine learning (ML): data is maintained on the owner's device and the updates to the model are aggregated through a secure protocol. However, this process assumes a trusted centralized infrastructure for coordination, and clients must…
Many of today's machine learning (ML) systems are not built from scratch, but are compositions of an array of {\em modular learning components} (MLCs). The increasing use of MLCs significantly simplifies the ML system development cycles. However, as most MLCs are contributed and maintained by third parties, their lack …
Defends against ML inference attacks using adversarial examples.
problem Automated inference attacks using ML classifiers pose privacy and security threats.
method Turns ML classifier vulnerabilities into defenses by adding adversarial noise to public data.
result Adversarial examples can mislead ML classifiers and protect private data.
Paper aims to bridge semantic gap between ML and InfoSec by labeling malware datasets with behavioral features.
problem Semantic gap between ML and InfoSec communities hinders ML's impact in InfoSec.
method Surveyed existing malware datasets and features, labeled with behavioral features using threat reports.
result Behavioral labeling alters analysis from intent to executable behavior, bridging semantic gap.
In machine learning (ML) security, attacks like evasion, model stealing or membership inference are generally studied in individually. Previous work has also shown a relationship between some attacks and decision function curvature of the targeted model. Consequently, we study an ML model allowing direct control over t…
Topology-aware generative models improve manifold-based defenses against adversarial examples.
problem Adversarial examples compromise the reliability of ML models, especially DNNs.
method Investigate if generative models used in manifold-based defenses need to be topology-aware.
result Topology-aware generative models enhance the robustness of manifold-based defenses.
Explainable machine learning (ML) enables human learning from ML, human appeal of automated model decisions, regulatory compliance, and security audits of ML models. Explainable ML (i.e. explainable artificial intelligence or XAI) has been implemented in numerous open source and commercial packages and explainable ML i…
Isthmus platform simplifies ML/AI integration in healthcare.
problem Challenges in deploying ML models in healthcare due to data quality, regulatory, and security issues.
method Turnkey, cloud-based platform addressing data quality, clinical relevance, and regulatory compliance.
result Reduces time to market for operationalizing ML/AI in healthcare.
Internet-of-Things (IoT) devices that are limited in power and processing are susceptible to physical layer (PHY) spoofing (signal exploitation) attacks owing to their inability to implement a full-blown protocol stack for security. The overwhelming adoption of multicarrier techniques such as orthogonal frequency divis…
Privacy is a major issue in learning from distributed data. Recently the cryptographic literature has provided several tools for this task. However, these tools either reduce the quality/accuracy of the learning algorithm---e.g., by adding noise---or they incur a high performance penalty and/or involve trusting externa…
Framework classifies machine learning failures into intentional and unintentional.
problem Understanding and preventing failures in machine learning systems.
method Developed a taxonomy of machine learning failure modes.
result Stakeholders found the framework useful for discussing machine learning failures.
This chapter is dedicated to the assessment and performance estimation of machine learning (ML) algorithms, a topic that is equally important to the construction of these algorithms, in particular in the context of cyberphysical security design. The literature is full of nonparametric methods to estimate a statistic fr…
With the widespread use of machine learning (ML) techniques, ML as a service has become increasingly popular. In this setting, an ML model resides on a server and users can query it with their data via an API. However, if the user's input is sensitive, sending it to the server is undesirable and sometimes even legally …
Paper proposes counterfactual explanations for ML on multivariate time series data.
problem Lack of user trust and difficulty in debugging ML frameworks using multivariate time series data.
method Proposes a novel explainability technique for providing counterfactual explanations.
result Outperforms state-of-the-art explainability methods in metrics like faithfulness and robustness.
Paper introduces proof-of-learning to verify ML model training.
problem No mechanism to prove ML model training parameters were obtained through optimization.
method Inspired by proof-of-work and verified computations, introduces proof-of-learning mechanism.
result Proves model training parameters were obtained through optimization with minimal adversary work.
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.
Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query interfaces. ML-as-a-service ("predictive analytics") systems are an example: Some …
As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which use hardware and software protections to isolate sensitive computations from the…
New dynamic backdoor attacks bypass current defenses.
problem Vulnerability of machine learning models to backdoor attacks.
method Random Backdoor, Backdoor Generating Network (BaN), and conditional Backdoor Generating Network (c-BaN).
result Dynamic backdoors can bypass current detection and defense mechanisms.
New framework explains ML credit scoring models using counterfactual examples.
problem Explaining complex ML models in finance for credit scoring.
method Adversarial counterfactual examples for tabular data.
result Proposes a method to generate realistic counterfactual examples for tabular data.
Develops fair feature importance scores for tree-based models to interpret fairness.
problem Ensuring fairness in machine learning models, especially tree-based ones.
method Inspired by decision trees, proposes a novel fair feature importance score based on mean decrease in group bias.
result Valid interpretations of fairness for tree-based ensembles and surrogates of other ML systems.
We study the problem of finding a universal (image-agnostic) perturbation to fool machine learning (ML) classifiers (e.g., neural nets, decision tress) in the hard-label black-box setting. Recent work in adversarial ML in the white-box setting (model parameters are known) has shown that many state-of-the-art image clas…
Detects malicious accounts in permissionless blockchains using graph properties and ML.
problem Identifying and classifying malicious accounts in permissionless blockchains.
method Temporal graph properties, ML algorithms (ExtraTreesClassifier, K-Means), cosine similarity, behavior change analysis.
result ExtraTreesClassifier performs best in detecting malicious accounts on Ethereum blockchain.
FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learningcs.LG
Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversar…
Unified framework for analyzing model stealing attacks and defenses.
problem Vulnerability of ML applications to model stealing attacks.
method Developed a rigorous threat model and evaluation criteria, proposed methods to quantify attack and defense strategies.
result Demonstrated the importance of attack-specific perturbations for effective defenses.
Randomized smoothing reduces accuracy in ML models, especially at higher noise levels.
problem Adversarial attacks on ML models, especially randomized smoothing's accuracy drop.
method Theoretical and empirical analysis of randomized smoothing's effect on feasible hypotheses space.
result For some noise levels, randomized smoothing shrinks the set of feasible hypotheses, leading to accuracy drops.
Paper evaluates membership inference attacks on transfer learning models.
problem Evaluating membership inference attacks on transfer learning models.
method Shadow model training strategy to derive data for membership inference classifier.
result Membership inference attacks can achieve effective performance against transfer learning models.
Probabilistic thermal stability prediction through sparsity promoting transformer representationstat.ML
Paper improves Tm prediction of protein fragments using sparsity and probabilistic models.
problem Improving accuracy of melting temperature prediction for protein fragments.
method Promoting sparsity in pre-trained transformer models and adopting probabilistic frameworks.
result Mean absolute error of 0.23C for predicting melting temperature.
Security-Constrained Unit Commitment (SCUC) is a fundamental problem in power systems and electricity markets. In practical settings, SCUC is repeatedly solved via Mixed-Integer Linear Programming, sometimes multiple times per day, with only minor changes in input data. In this work, we propose a number of machine lear…
Paper examines how adversarial ML attacks and defenses impact civil liberties and human rights.
problem Impact of adversarial machine learning on civil liberties and human rights.
method Uses insights from STS, anthropology, and human rights literature.
result Adversarial defenses can be used to suppress dissent and limit investigation of ML systems.
Framework for AI customer support that protects privacy and reduces costs.
problem Privacy risks and compliance challenges in AI customer support.
method Zero-shot learning with large language models, real-time data anonymization, retrieval-augmented generation, robust post-processing.
result Reduces privacy risks and compliance costs while maintaining accuracy.
Paper introduces attacks to infer GAN training dataset properties.
problem Security and privacy risks of generative models like GANs.
method Proposes a general attack pipeline for two attack scenarios.
result Demonstrates strong performance in inferring GAN training dataset properties.