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. 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.
Efficiently estimates sparse linear regression with heavy-tailed data and outliers.
problem Sparse estimation of linear regression coefficients with heavy-tailed covariates and noises, including outliers.
method Efficient computation of robust estimator with nearly optimal error bound.
result Nearly optimal error bound for robust sparse estimation.
We study two problems in high-dimensional robust statistics: \emph{robust mean estimation} and \emph{outlier detection}. In robust mean estimation the goal is to estimate the mean μ of a distribution on Rd given n independent samples, an ε-fraction of which have been corrupted by a malicious…
We consider the problem of learning from noisy data in practical settings where the size of data is too large to store on a single machine. More challenging, the data coming from the wild may contain malicious outliers. To address the scalability and robustness issues, we present an online robust learning (ORL) approac…
New algorithm detects network outliers with missing links.
problem Identifying outliers in networks with missing links.
method Proposes a new algorithm that detects outliers and predicts missing links.
result Proves the algorithm exactly detects outliers and achieves best error for missing link prediction.
RTVAE uses β-divergence to detect anomalies in tabular data robustly.
problem Outliers in tabular data affect VAE training and anomaly detection.
method Robust VAE with β-divergence for mixed categorical and continuous features.
result Demonstrates effectiveness on network traffic anomaly detection.
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.
Heavy-tailed outliers are more resilient to robust estimation than adversarial ones.
problem Developing robust estimators for data with outliers.
method Analyzing the relationship between adversarial and heavy-tailed outlier models.
result Optimal estimators for heavy-tailed outliers are also optimal for adversarial settings, but not vice versa.
Survey of AI-based outlier detection methods for various domains.
problem Detecting unusual events to prevent infrastructure damage.
method Categorizes six major OD methods: Statistical, Distance, Density, Clustering, Learning, and Ensemble.
result Advances and challenges of each method discussed.
We consider the problems of robust PAC learning from distributed and streaming data, which may contain malicious errors and outliers, and analyze their fundamental complexity questions. In particular, we establish lower bounds on the communication complexity for distributed robust learning performed on multiple machine…
We consider high dimensional sparse regression, and develop strategies able to deal with arbitrary -- possibly, severe or coordinated -- errors in the covariance matrix X. These may come from corrupted data, persistent experimental errors, or malicious respondents in surveys/recommender systems, etc. Such non-stochas…
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.
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.
Singular Value Decomposition (and Principal Component Analysis) is one of the most widely used techniques for dimensionality reduction: successful and efficiently computable, it is nevertheless plagued by a well-known, well-documented sensitivity to outliers. Recent work has considered the setting where each point has …
New method for robust PCA with exponential family distributions.
problem Recovering low-rank structure from data matrices with outliers.
method Alternating Direction Method of Multipliers for eextRPCA. result Demonstrated effectiveness in steel sheet defect detection and crime activity monitoring.
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.
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. Christoffel function characterizes the corruption a bounded-degree certificate cannot remove in robust halfspace learning.
problem Robust halfspace learning under malicious noise
method Sum-of-Squares degree of outlier-removal certificate
result Christoffel function bounds the corruption a bounded-degree certificate cannot remove
Byrd-SAGA reduces variance to robustify SGD against Byzantine attacks.
problem Learning over networks with malicious Byzantine attacks.
method Byrd-SAGA uses geometric median for robust aggregation of corrected stochastic gradients.
result Byrd-SAGA achieves provably linear convergence to optimal solution in the presence of Byzantine workers.
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.
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.
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…
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…
Detection of malware-infected computers and detection of malicious web domains based on their encrypted HTTPS traffic are challenging problems, because only addresses, timestamps, and data volumes are observable. The detection problems are coupled, because infected clients tend to interact with malicious domains. Traff…
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.
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.
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.
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.
As the prevalence and everyday use of machine learning algorithms, along with our reliance on these algorithms grow dramatically, so do the efforts to attack and undermine these algorithms with malicious intent, resulting in a growing interest in adversarial machine learning. A number of approaches have been developed …
On the path to establishing a global cybersecurity framework where each enterprise shares information about malicious behavior, an important question arises. How can a machine learning representation characterizing a cyber attack on one network be used to detect similar attacks on other enterprise networks if each netw…
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. Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms to extract valuable information from data and produce accurate predictions, it ha…
Phishing is the simplest form of cybercrime with the objective of baiting people into giving away delicate information such as individually recognizable data, banking and credit card details, or even credentials and passwords. This type of simple yet most effective cyber-attack is usually launched through emails, phone…
An important problem in networked systems is detection and removal of suspected malicious nodes. A crucial consideration in such settings is the uncertainty endemic in detection, coupled with considerations of network connectivity, which impose indirect costs from mistakely removing benign nodes as well as failing to r…
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.
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…
New approach shows backdoor attacks are indistinguishable from natural data features.
problem Defending against backdoor attacks in machine learning models.
method Developed a new primitive for detecting backdoor attacks based on the assumption that they correspond to the strongest feature in the training data.
result Backdoor attacks are indistinguishable from natural data features, making traditional detection methods ineffective.
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. 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.
With the rapid proliferation and increased sophistication of malicious software (malware), detection methods no longer rely only on manually generated signatures but have also incorporated more general approaches like machine learning detection. Although powerful for conviction of malicious artifacts, these methods do …
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.
Machine Learning (ML) models are applied in a variety of tasks such as network intrusion detection or Malware classification. Yet, these models are vulnerable to a class of malicious inputs known as adversarial examples. These are slightly perturbed inputs that are classified incorrectly by the ML model. The mitigation…
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).