New framework detects and removes malicious model updates in federated learning.
problem Vulnerability of federated learning systems to malicious client attacks.
method Central server learns to detect and remove malicious model updates using a detection model.
result Ensures robust federated learning resilient to Byzantine and targeted model poisoning attacks.
Detects malware-infected clients and malicious domains using transfer learning.
problem Detecting malware-infected computers and malicious web domains from encrypted HTTPS traffic.
method Transfer learning with sluice networks to bootstrap each other's detection models.
result Outperforms known reference models and detects previously unknown malware and domains.
Study uses online data to identify malicious websites, addressing imbalance.
problem Identifying malicious websites from many more benign ones.
method Integrated resampling approach combining SMOTE and PSO.
result Proposed approach outperforms other resampling methods.
Paper proposes efficient privacy-preserving matrix encryption for secure collaborative learning against malicious adversaries.
problem Secure collaborative learning of sensitive data across different agencies is challenging with malicious adversaries.
method The paper applies matrix encryption to secure data against chosen plaintext attack, known plaintext attack, and collusion attack, achieving local differential privacy and high computation efficiency.
result The proposed schemes are computationally efficient and secure against malicious adversaries compared to existing techniques.
Hybrid approach combines ASTs and deep learning for PowerShell malware detection.
problem Detecting malicious PowerShell scripts effectively.
method Combining static program analysis (ASTs) with deep learning.
result Preliminary results show promising classification of PowerShell scripts by family type.
New algorithm reduces regret in multi-agent bandits with malicious agents.
problem Collaboration between honest and malicious agents in multi-armed bandits.
method Dynamic reduction of communication with malicious agents, learning who is malicious.
result Algorithm reduces regret even with a single malicious agent, assuming m is small compared to K. Efficient active learning method defends against malicious mislabeling and data poisoning attacks.
problem Malicious mislabeling and data poisoning attacks on deep neural networks.
method Adversarial retraining and active learning with random sampling strategy.
result The proposed method achieves 89% accuracy with only one-third of the labeled data, significantly outperforming the baseline method.
Data poisoning attacks can severely degrade FL models, especially targeting specific classes.
problem Data poisoning attacks against federated learning systems.
method Demonstrated targeted attacks on FL systems, analyzed attack longevity, and proposed a defense strategy.
result Data poisoning attacks can cause substantial drops in classification accuracy and recall with a small percentage of malicious participants.
Optimal policies identified for learning systems with a malicious expert.
problem Adversarial attacks on learning systems combining expert advice.
method Analysis of offline and online settings, dynamic programming for online setting.
result Greedy policy is asymptotically optimal with approximation ratio for offline setting.
New method detects and measures malicious users in recommendation algorithms.
problem Identifying and quantifying malicious user activity in recommendation systems.
method Probabilistic programming for a disentangled model of malicious and regular user behavior.
result Simulation-based measure for quantifying malicious user effects.
The paper uses machine learning to detect malicious executable files.
problem Detecting malicious executable files using static analysis.
method Pre-processing, cleaning, encoding, feature selection, and ensemble training of classifiers.
result An ensemble of classifiers effectively detects malicious executable files.
This paper uses deep reinforcement learning to detect phishing websites.
problem Detecting and preventing phishing websites to protect user data.
method Introduces a novel deep reinforcement learning model for phishing website detection.
result The model can adapt to the dynamic nature of phishing websites.
Adversarial neural network improves cyber attack detection across different networks.
problem Detecting cyber attacks across networks with different traffic distributions.
method Adversarial Siamese neural network that learns invariant attack representations.
result The method retrieves sizable proportions of malicious events, even when trained on one dataset and tested on another.
GEM detects malicious accounts using adaptive embeddings from heterogeneous graphs.
problem Detecting malicious accounts on a leading mobile payment platform.
method Adaptive learning of discriminative embeddings from heterogeneous account-device graphs with attention mechanism for node importance.
result GEM consistently outperforms competitive methods in detecting malicious accounts.
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.
Machine learning detects phishing websites by identifying common characteristics.
problem Phishing websites deceive users and steal sensitive information.
method Compared multiple machine learning methods for predicting phishing websites.
result Machine learning can identify common characteristics of phishing websites.
Study efficient learning of halfspaces with constant noise tolerance.
problem Learning halfspaces in the presence of both instance and label corruption.
method Develops an algorithm to minimize reweighted hinge loss for robustness.
result Achieves constant noise tolerance for halfspace learning.
Improved sample complexity for learning halfspaces with malicious noise.
problem Efficiently learning halfspaces in the presence of malicious noise.
method New analysis of Awasthi et al. algorithm with matrix Chernoff inequality and localization schemes.
result Achieved near-optimal sample complexity of ildeO(d) for isotropic log-concave distributions. Efficiently learns halfspaces with malicious noise, near-optimal label complexity.
problem Learning s-sparse halfspaces under malicious label noise. method Active learning algorithm with instance reweighting and empirical risk minimization.
result Near-optimal label complexity of O(slog4d/ε) and noise tolerance Ω(ε). Federated learning is vulnerable to model poisoning attacks by a single malicious agent.
problem Vulnerability of federated learning to model poisoning attacks by a single non-colluding agent.
method Exploration of model poisoning attacks, including boosting, alternating minimization, and parameter estimation.
result Even a constrained adversary can successfully carry out model poisoning attacks while maintaining stealth.
Bayesian framework robustifies classifiers against malicious attacks.
problem Adversarial attacks on classification algorithms in security and business.
method Adversarial risk analysis and approximate Bayesian computation.
result Robustifies statistical classification algorithms against attacks.
FLANDERS detects and blocks extreme model poisoning in federated learning.
problem Resilience against large-scale model poisoning attacks in federated learning.
method FLANDERS treats client updates as matrix-valued time series and identifies outliers using autoregressive forecasting.
result FLANDERS significantly improves robustness in federated learning across various attacks.
New method tags malware for better understanding and identification.
problem Lack of detailed descriptions and relationships between malware samples.
method Deep learning model generates human-interpretable descriptions and similarity index.
result Correctly identifies more than 95% of eleven tag descriptions with a low false positive rate.
A system predicts future malicious behavior of network entities.
problem Prioritizing alert data and understanding attack recurrence.
method Machine learning-based network entity reputation database system.
result It is possible to precisely estimate future attack probabilities.
New method robustly removes malicious nodes from networks considering uncertainty.
problem Detect and remove malicious nodes in networks considering uncertainty and indirect costs.
method Distributionally robust framework using duality and Semidefinite Programming relaxation.
result Algorithm is highly effective and significantly more robust than state of the art.
Nowadays, machine learning based Automatic Speech Recognition (ASR) technique has widely spread in smartphones, home devices, and public facilities. As convenient as this technology can be, a considerable security issue also raises -- the users' speech content might be exposed to malicious ASR monitoring and cause seve…
New algorithm reduces regret in multi-agent bandits over undirected graphs.
problem Minimize regret in a multi-agent bandit setting with malicious agents.
method Proposed a new algorithm for undirected graphs, considering the number of malicious neighbors.
result The new algorithm achieves nearly linear regret improvement over existing methods.
We introduce a new approach for designing computationally efficient learning algorithms that are tolerant to noise, and demonstrate its effectiveness by designing algorithms with improved noise tolerance guarantees for learning linear separators. We consider both the malicious noise model and the adversarial label nois…
ERM and RERM minimize error even with malicious label corruptions.
problem Malicious label corruptions in regression problems.
method Empirical Risk Minimizers (ERM) and Regularized Empirical Risk Minimizers (RERM) under a local Bernstein condition.
result The L2-error rate is bounded by $r_N + AL |\cO|/N$ under the local Bernstein condition. This paper proposes a generic classification system designed to detect security threats based on the behavior of malware samples. The system relies on statistical features computed from proxy log fields to train detectors using a database of malware samples. The behavior detectors serve as basic reusable building block…
A new federated learning framework ensures fairness and robustness.
problem Collaborative fairness and adversarial robustness in federated learning.
method RFFL framework with a reputation mechanism to identify and remove non-contributing or malicious participants.
result RFFL achieves high fairness and robustness to different types of adversaries.
The amount of personal data collected in our everyday interactions with connected devices offers great opportunities for innovative services fueled by machine learning, as well as raises serious concerns for the privacy of individuals. In this paper, we propose a massively distributed protocol for a large set of users …
Malicious agents can manipulate linear contextual bandits to pull desired arms with logarithmic overhead.
problem Malicious attacks on linear contextual bandit algorithms in various domains.
method Study and propose an efficient algorithm to perform adversarial attacks on linear contextual bandits.
result Malicious agents can force a linear contextual bandit algorithm to pull any desired arm T−o(T) times over a horizon of T steps with logarithmic modifications. 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.
Paper examines vulnerabilities in data-driven pricing schemes.
problem Vulnerability of clustering-oriented pricing schemes to malicious user behavior.
method Defined a notion of disguising to identify strategic behaviors of malicious users, characterized sensitivity zones to evaluate malicious user percentages, conducted cost benefit analysis.
result Concluded with a vulnerability analysis of data-driven pricing schemes.
RW-based learning is vulnerable to the Pac-Man attack, which eliminates active RWs.
problem Vulnerability of RW-based learning to malicious behavior.
method Proposed the Average Crossing (AC) algorithm to prevent RW extinction.
result RW-based stochastic gradient descent remains convergent under AC, even in the presence of Pac-Man.
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that can compromise its integrity and efficiency. Security attacks can be divided bas…
BlockFLow ensures privacy and accountability in federated learning.
problem Malicious agents can weaken federated learning models.
method Differential privacy, auditing mechanism, Ethereum smart contracts.
result Audit scores reflect the quality of honest agents' datasets.
MatchGNet detects malware by learning program behavior graphs.
problem Malware evasion through obfuscation and high false positives in traditional detection methods.
method Heterogeneous Graph Matching Network model that learns graph representation and similarity metrics.
result MatchGNet reduces false positives by 50% while maintaining zero false negatives.
Improved malware detection by adding auxiliary loss terms to a neural network.
problem Malware detection accuracy with a single label.
method Fit deep neural networks to multiple auxiliary prediction targets derived from metadata.
result Significant improvement in detection performance, reducing false negatives by 42.6% at a low false positive rate.
New algorithm detects and discards faulty updates in federated learning.
problem Byzantine failures, biased local datasets, and poisoning attacks in federated learning.
method Adaptive Federated Averaging with Hidden Markov Model for quality update detection.
result Significantly more robust to faulty, noisy, and malicious participants.
Detects potential rug pulls in Uniswap tokens before they occur.
problem Rug pulls in Uniswap, a decentralized exchange, leading to token scams.
method Collects and analyzes 20K transactions, proposes machine learning algorithms with new features.
result Achieved an accuracy of 0.9936 in detecting potential scams before they happen.
New approach simulates reputation dynamics using information compression.
problem Malicious communication strategies in reputation networks.
method Uses information compression techniques to simulate social phenomena.
result Emergent phenomena like echo chambers and deception are observed.
Detects backdoors in outsourced models by replicating training steps across multiple servers.
problem Detecting backdoors in models trained on cloud providers without prior knowledge.
method Replicate training steps across multiple servers to identify deviations and malicious updates.
result 99.6% accuracy in identifying backdoored models out of 50% malicious providers.
New aggregation methods improve robustness and efficiency in distributed learning.
problem Outliers and malicious agents compromise traditional averaging in distributed learning.
method Developed statistically efficient and robust aggregation schemes based on median and trimmed mean variations.
result Achieved higher sample efficiency compared to traditional robust aggregation schemes.
Paper tackles Byzantine attacks in distributed learning with a new ADMM method.
problem Byzantine workers sending arbitrary messages bias distributed learning.
method Byzantine-robust stochastic ADMM exploiting separable problem structure.
result Proposed method converges to optimal solution at O(1/k) rate.
Paper proposes SDS for 5G security using machine learning.
problem Cybersecurity threats and expanding IoT in 5G networks.
method SDS uses machine learning, specifically a CNN with NAS, to detect anomalies.
result CNN achieved 100% accuracy in identifying benign traffic and 96.4% in detecting anomalies.
Study examines unsupervised and graph-based methods for anomaly detection in IoBT, outperformed by supervised stacking ensemble.
problem Anomaly detection in adversarial environments of IoBT.
method Unsupervised learning, graph-based methods, ensemble supervised learning, adversarial training.
result Supervised stacking ensemble method outperforms unsupervised and graph-based methods in detecting anomalies.