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.
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.
With the celebrated success of deep learning, some attempts to develop effective methods for detecting malicious PowerShell programs employ neural nets in a traditional natural language processing setup while others employ convolutional neural nets to detect obfuscated malicious commands at a character level. While the…
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.
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.
A(DP)2SGD improves federated learning privacy and efficiency.
problem Privacy and efficiency in federated learning with asynchronous decentralized parallel SGD.
method Differentially private asynchronous decentralized parallel SGD (A(DP)2SGD) using R{é}nyi differential privacy. result Achieves optimal convergence rate and comparable model accuracy to SSGD but faster.
Distributed model training is vulnerable to byzantine system failures and adversarial compute nodes, i.e., nodes that use malicious updates to corrupt the global model stored at a parameter server (PS). To guarantee some form of robustness, recent work suggests using variants of the geometric median as an aggregation r…
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.
Proposes a trust model for SIoT nodes using Hellinger distance and matrix factorization.
problem Trust management in SIoT to reduce risk from malicious nodes.
method Flexible bipartite graph, Hellinger distance, centrality, similarity measures, matrix factorization.
result The proposed trust prediction mechanism outperforms existing methods in accuracy and resilience.
Generates low-dimensional node vectors for graphs with privacy while preserving structural preferences.
problem Publishing graph node vectors can leak sensitive individual information.
method SE-PrivGEmb, a skip-gram based technique with a unified noise tolerance mechanism and negative sampling probabilities.
result Our method outperforms existing methods in structural equivalence and link prediction tasks.
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. 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.
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.
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.
Purpose: Malicious web domain identification is of significant importance to the security protection of Internet users. With online credibility and performance data, this paper aims to investigate the use of machine learning tech-niques for malicious web domain identification by considering the class imbalance issue (i…
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.
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.
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.
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.
Proposes a method to improve Byzantine-robustness in compressed federated learning.
problem Byzantine-robustness in compressed federated learning.
method Gradient difference compression and stochastic average gradient algorithm (SAGA).
result The proposed method reaches a neighborhood of the optimal solution at a linear convergence rate.
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. Adversarial inference on tree models is possible with limited corruption, improving on Kesten-Stigum threshold.
problem Posterior inference on tree-structured graphical models in the presence of adversarial corruption.
method Dynamic programming via belief propagation, constrained adversarial corruption.
result Belief propagation can perform accurate inference with limited adversarial corruption.
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.
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.
Grale designs graphs for graph learning, improving performance on large datasets.
problem Finding the right graph for semi-supervised learning with billions of nodes.
method Fuses multiple similarity measures using locality sensitive hashing to create task-specific graphs.
result Grale detects a large number of malicious actors, increasing recall by 89%.
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…
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. Novel method HAO mitigates Graph Injection Attack by preserving homophily.
problem Graph Injection Attack's high flexibility can harm graph homophily.
method Introduce homophily unnoticeability constraint and Harmonious Adversarial Objective (HAO).
result GIA with HAO breaks homophily-based defenses and outperforms previous attacks.
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.
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.
FAdeML shows pre-processing noise filters can mitigate adversarial attacks.
problem Lack of security in DNN-based ML systems due to adversarial attacks.
method Proposes FAdeML, a novel pre-processing noise Filter-aware Adversarial ML attack.
result Demonstrates that pre-processing noise filters can render ineffective most adversarial attacks.
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.
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.
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). 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.
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.
DICE estimates data influence cascade in decentralized learning networks.
problem Lack of fair incentives discourages participation in decentralized learning.
method Designs DICE to estimate influence cascade in decentralized networks.
result Influence cascade is influenced by data, topology, and loss landscape curvature.
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 …
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…
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.
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…
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.
This article reviews recent advances in secure distributed and decentralized inference and learning against Byzantine threats.
problem Securing distributed and decentralized inference and learning against malicious attacks.
method Review of recent algorithmic approaches under Byzantine threat model.
result A plethora of robust algorithmic approaches have been developed.