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.
Abstract: Cyber-security challenges tackled with machine learning.
problem Cyber-security problems and lack of labeled data.
method Provided novel data sets and a method to generate labels via pivoting.
result Solutions for generating labels in cyber-security.
This paper discusses adversarial attacks on cyber security systems using machine learning.
problem Adversarial attacks limit the use of machine learning in cyber security.
method Characterizes adversarial attack methods and their applications in cyber security.
result Highlights unique challenges and future research directions for adversarial attacks in cyber security.
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.
secml is a Python library for secure and explainable machine learning.
problem Evaluate and understand security and explainability of machine learning models.
method Implement attacks and explainability methods for various algorithms.
result Demonstrates how quickly models fail under adversarial perturbations and visualizes influential features.
Research tests machine learning models for cloud security.
problem Lack of real-time, unbiased datasets for machine learning in cloud security.
method Used UNSW and ISOT datasets to train and test supervised machine learning models.
result Machine learning models trained on diverse datasets show robustness in cloud security.
This paper explores security threats in ML systems and proposes mitigation techniques.
problem Security vulnerabilities in ML-based systems during training and inference.
method Overview of security threats, demonstrations using LeNet and VGGNet, proposed attack.
result Demonstrated security threats and proposed mitigation techniques.
New method defends machine learning models from black-box attacks.
problem Protecting machine learning models from black-box transfer attacks.
method Randomized ensemble technique with provable security guarantee.
result Empirical evidence of security for random binary classifiers.
Paper proposes a secure protocol for federated learning.
problem Combining robustness, privacy, and security in federated learning.
method Secure two-server protocol for federated learning.
result Offers both input privacy and Byzantine-robustness.
Secure and efficient distributed learning on devices with limited communication.
problem Limited communication and security in distributed on-device learning.
method Proposes SLSGD, a robust distributed optimization algorithm with efficient communication and attack tolerance.
result Stabilizes convergence and tolerates data poisoning on a small number of workers.
Securely share encrypted data for machine learning training.
problem Securely sharing encrypted data for machine learning training without revealing the data.
method Rotation based method using flow model.
result Theoretical justification and demonstration of effectiveness in different scenarios.
Secure XGB for privacy-preserving machine learning in federated learning.
problem Privacy-preserving machine learning in federated learning with practical gradient tree boosting models.
method Secure multi-party computation, distributed model storage, secure permutation protocols.
result Our XGB models provide competitive accuracy and practical performance.
This paper reviews adversarial attacks on ML and DL models.
problem Adversarial attacks on ML and DL models.
method Review of existing adversarial attacks and perturbations.
result Comprehensive understanding of adversarial security attacks on ML and DL.
This paper reviews ML and DL for IoT security, highlighting gaps and future directions.
problem Security and privacy issues in IoT networks due to resource constraints and dynamic behavior.
method Systematic review of current security solutions and ML/ DL approaches.
result ML and DL are essential for IoT security due to resource constraints and dynamic behavior.
This work develops secure distributed algorithms for machine learning to protect against data poisoning and network attacks.
problem Vulnerability of distributed machine learning algorithms to cyber threats.
method Game-theoretic framework to capture conflicting goals of a learner and an attacker, iterative distributed algorithm.
result Distributed SVM is prone to fail in different types of attacks, with impact depending on network structure and attack capabilities.
Study proposes hybrid machine learning models for crop yield prediction.
problem Crop yield prediction for food security.
method Hybrid machine learning models (ANN-ICA and ANN-GWO).
result ANN-GWO model outperformed ANN-ICA in crop yield prediction.
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.
Secure transfer learning framework improves model flexibility without compromising privacy.
problem Scattered data across organizations limits machine learning.
method Federated Transfer Learning (FTL) framework with secure transfer cross validation.
result Models can be built more flexibly and accurately with shared labels from different sources.
Paper offers guidelines for using ML in cyber security, focusing on botnet detection.
problem Lack of public benchmark datasets for evaluating ML-based cyber security systems.
method Provided concrete guidelines and recommendations for using supervised ML in cyber security, focusing on botnet detection.
result Ensemble models are well-suited to handle class imbalance in botnet detection.
This research secures deployed sentiment analysis models by identifying and defending against attack vectors.
problem Securing deployed machine learning models, particularly sentiment analysis systems, from adversarial attacks.
method BAD (Build, Attack, Defend) Architecture, evaluating two implementations.
result Demonstrated a viable methodology for securing machine learning models in production.
Reducing features weakens adversarial attacks, improving security but at the cost of accuracy.
problem Adversarial attacks on machine learning models.
method Empirical evaluation and design methodology for feature selection.
result Reducing features increases the difficulty of adversarial attacks.
Deep RL enhances cyber security through adaptive, responsive, and scalable defenses.
problem Complex, dynamic cyber attacks require adaptive and scalable security solutions.
method Incorporates deep learning into traditional RL for cyber defense.
result Demonstrates the potential of DRL in solving high-dimensional cyber defense problems.
Dynamic models defend against correlated attacks in machine learning.
problem Securing machine learning models against adversarial inputs when input distribution is not independent.
method Dynamic models that change each time they are run.
result Simple dynamic defense mitigates correlated attack.
Paper proposes NeuroAttack to undermine SNNs security through bit-flips.
problem Security and reliability issues in SNNs.
method Cross-layer attack exploiting low-level reliability issues via adversarial input noise.
result Serious integrity threat to SNNs and DNNs.
This paper surveys adversarial machine learning focusing on deep learning.
problem How adversarial attacks can cause deep learning models to make mistakes.
method Comprehensive review of adversarial attacks and defenses in deep learning.
result Adversarial attacks can lead to significant errors in deep learning models.
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.
To assure cyber security of an enterprise, typically SIEM (Security Information and Event Management) system is in place to normalize security event from different preventive technologies and flag alerts. Analysts in the security operation center (SOC) investigate the alerts to decide if it is truly malicious or not. H…
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.
Secure federated learning framework resists adversarial users.
problem Resilience against adversarial (Byzantine) users in federated learning.
method Integrated stochastic quantization, verifiable outlier detection, and secure model aggregation.
result First single-server Byzantine-resilient secure aggregation framework (BREA) for secure federated learning.
This paper tackles security challenges in CAVs using ML, proposing defenses against adversarial attacks.
problem Security threats posed by adversarial machine learning in CAVs.
method An in-depth analysis of ML pipeline in CAVs, identifying security issues and proposing defenses.
result Proposes solutions to defend against adversarial attacks in CAVs.
We develop a secure aggregation protocol for federated learning that reduces communication and computation costs.
problem Expensive communication and privacy concerns in federated learning.
method Adapting compression-based federated techniques to additive secret sharing.
result Our protocol achieves high accuracy with low communication costs and is more efficient than prior work.
HASP enhances mobile security against ASR by adding imperceptible noise.
problem Security leakage from ASR on mobile devices.
method Adversarial noise to perturb WER and enhance security.
result HASP reduces WER by 84.55% and speeds up data processing.
The paper evaluates methods for explaining deep learning in security.
problem Understanding the predictions of deep learning models in security applications.
method Developed criteria to compare and evaluate six explanation methods.
result Significant differences exist between the methods, leading to recommendations.
This paper reviews integrating blockchain and machine learning.
problem Secure and efficient data sharing and analysis in blockchain.
method Review of existing research and demonstration of collaboration.
result Blockchain and machine learning can collaborate efficiently and effectively.
Wrist movements can reveal digits, posing security risks.
problem Security vulnerabilities in wrist wearable devices.
method Machine learning model trained on wrist movement data.
result 100% accuracy in predicting digits via wrist movement.
Hardware Trojans can fool neural networks, affecting security.
problem Security vulnerabilities in hardware optimized neural networks.
method Developed a framework for inserting malicious hardware Trojans in neural network classifiers.
result Trojans can fool neural networks with minimal impact, affecting 0.03% of neurons.
New model improves classifier security against evasion attacks by selecting features.
problem Security of machine learning classifiers against evasion attacks.
method Adversary-aware feature selection model incorporating specific adversary assumptions.
result Classifier security worsens with feature selection, but new model improves it.
This paper improves federated learning efficiency by auto-tuning secure aggregation parameters.
problem Efficient communication in federated learning with quantized updates.
method Auto-tuning secure aggregation parameters based on random rotation properties.
result Improved communication efficiency in federated learning with secure aggregation.
Distributed Support Vector Machines (DSVM) have been developed to solve large-scale classification problems in networked systems with a large number of sensors and control units. However, the systems become more vulnerable as detection and defense are increasingly difficult and expensive. This work aims to develop secu…
Federated Extra-Trees protects privacy while improving machine learning performance.
problem Scattered data and privacy concerns in machine learning.
method Local differential privacy in federated trees model.
result Improved accuracy and robustness in federated machine learning.
CodedPrivateML secures ML training data and models.
problem Training machine learning models while keeping data private.
method Data and model-theoretically private approach with parallelization.
result Significant speedup over cryptographic methods.
MLCapsule protects sensitive data by executing models locally.
problem Protecting sensitive data and model security in MLaaS.
method Local execution of models on client side, coupled with security measures.
result Models executed locally without data leaving the client, protecting against attacks.
QFNN-FFD uses quantum computing and FL for secure financial fraud detection.
problem Financial fraud detection in the financial sector.
method Quantum Federated Neural Network (QFNN-FFD) combining QML and FL.
result Achieves precision rates above 95% and robustness against noise.
Secure methods learn fair models without revealing sensitive attributes.
problem Training fair machine learning models without exposing sensitive data.
method Secure multi-party computation to encrypt sensitive attributes.
result Outcome-based fair models can be learned, checked, or verified without revealing sensitive attributes.
Study on how changing curvature of GPC affects different types of attacks.
problem Understanding the relationship between different test-time attacks on GPCs.
method Examined Gaussian Process classifiers and their vulnerability to various attacks.
result Changing curvature of GPCs can make it robust against some attacks but vulnerable to others.
Differential privacy improves AI security, fairness, and learning.
problem Privacy violations, security issues, and model fairness in AI.
method Application of differential privacy in various AI areas.
result Differential privacy enhances AI performance in multiple areas.
Biscotti uses blockchain for secure peer-to-peer ML without central coordination.
problem Secure and private multi-party machine learning with trust and poisoning attacks.
method Decentralized peer-to-peer ML using blockchain and cryptography.
result Biscotti protects privacy and model performance against 30% adversaries.