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. Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper, we break two prevailing Byzantine-tolerant techniques. Specifically we show robu…
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 …
New method improves reliability of recommender systems in face of fake accounts and manipulation.
problem Improving reliability of recommender systems in the presence of fake accounts and manipulation.
method Robust Discrete Matrix Completion (RDMC) method designed to handle sparse rating data and manipulation.
result Evaluations show RDMC offers a statistically-sound blueprint for future studies on recommender systems.
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.
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…
Trojans can be inserted into deep neural networks without altering training data.
problem Inserting malicious code into deep learning models without changing training data.
method Patches model parameters in memory to achieve desired behavior on specific inputs.
result Efficient patches can induce trojan behavior with minimal risk of detection.
With the ever-increasing reliance on data for data-driven applications in power grids, such as event cause analysis, the authenticity of data streams has become crucially important. The data can be prone to adversarial stealthy attacks aiming to manipulate the data such that residual-based bad data detectors cannot det…
This paper considers the problem of matrix completion when some number of the columns are completely and arbitrarily corrupted, potentially by a malicious adversary. It is well-known that standard algorithms for matrix completion can return arbitrarily poor results, if even a single column is corrupted. One direct appl…
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.
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. 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.
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…
This paper evaluates targeted data poisoning attacks by focusing on the hardest samples, improving evaluation and defense strategies.
problem The effectiveness of targeted data poisoning attacks is often overestimated due to average evaluation methods.
method The paper introduces metrics to identify the hardest and easiest to poison samples based on clean model information.
result The proposed metrics reliably stratify samples by poisoning vulnerability, enabling rigorous worst-case evaluation and proactive defense.
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…
This paper studies robust payoff allocation in submodular games, especially against replication.
problem Payoff allocation in submodular games, especially robustness against replication.
method Systematically studied replication manipulation in submodular games, introduced replication robustness metric, and validated with empirical ML data market.
result Conditions characterizing robustness of semivalues in submodular games.
New defense mechanism detects and mitigates poisoned regression data.
problem Vulnerability of regression models to targeted data poisoning attacks.
method Introduces N-LID, a measure of local intrinsic dimensionality to distinguish poisoned samples.
result N-LID based defense outperforms state-of-the-art methods in prediction accuracy and runtime.
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.
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.
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.
Backdoor attacks are possible in feature-partitioned collaborative learning, even without labels.
problem Backdoor attacks in feature-partitioned collaborative learning.
method Demonstrated the feasibility of backdoor attacks and introduced defense techniques.
result Backdoor attacks can be blocked without significantly affecting main task accuracy.
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…
This work proposes a robust ensemble method for decision trees that resists adversarial attacks.
problem Adversarial attacks on machine learning models, especially decision trees.
method Feature partitioning to train robust ensembles and approximate certification methods.
result The proposed ensemble method can resist evasion attacks by a majority of its models.
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.
Certain research strands can yield "forbidden knowledge". This term refers to knowledge that is considered too sensitive, dangerous or taboo to be produced or shared. Discourses about such publication restrictions are already entrenched in scientific fields like IT security, synthetic biology or nuclear physics researc…
The paper examines how to protect LASSO-based feature selection from adversarial attacks.
problem Adversarial attacks on LASSO-based feature selection.
method Formulated as a bi-level optimization problem, reformulated LASSO with linear inequality constraints, solved using interior-point method, and modified using projected gradient descent.
result Demonstrated the effectiveness of the proposed method in protecting LASSO-based feature selection from adversarial attacks.
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…
AI learns market manipulation through simulation, suggesting regulation.
problem Regulating AI to prevent market manipulation.
method Used a genetic algorithm in an artificial market simulation.
result AI discovered market manipulation as an optimal strategy.
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 models have been recently used for detecting malicious Android applications, reporting impressive performances on benchmark datasets, even when trained only on features statically extracted from the application, such as system calls and permissions. However, recent findings have highlighted the fragili…
Game theory models incentivizes honesty in collaborative learning among competitors.
problem Incentivizing honest updates among competitors in collaborative learning schemes.
method Formulated a game to model interactions, studied two learning tasks, proposed mechanisms to incentivize honest communication.
result Rational clients are incentivized to manipulate their updates, preventing learning; proposed mechanisms ensure comparable learning quality to full cooperation.
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.
The paper analyzes how leverage affects manipulation in event-linked markets, offering new insights into regulation.
problem Manipulation and insider information in leveraged event-linked markets.
method Develops a two-axis manipulation taxonomy and analyzes leverage's effects on market-price and outcome manipulation.
result Leverage scales market-price manipulation linearly but shifts the cost-benefit threshold for outcome manipulation.
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 model improves neural network robustness against input manipulations.
problem Improving neural network robustness against input manipulations.
method Causal view and deep causal manipulation augmented model (deep CAMA) with data augmentation and test-time fine-tuning.
result Deep CAMA shows superior robustness against unseen manipulations compared to traditional models.
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. Robust CLIP improves vision models' resistance to attacks.
problem Vulnerability of vision models to adversarial attacks.
method Unsupervised adversarial fine-tuning of CLIP.
result Robust CLIP prevents stealth attacks on vision models.
This paper studies poisoning attacks in episodic RL and discovers their effectiveness depends on reward bounds.
problem Understanding security threats to RL algorithms through poisoning attacks.
method Examined two types of poisoning attacks: reward and action manipulation, in bounded and unbounded reward settings.
result The effectiveness of poisoning attacks depends on reward bounds, with different attack costs and success rates.
New adversarial training enhances malware detectors against various attacks.
problem Vulnerability of malware detectors to evasion attacks.
method Proposes a mixture of attacks and adversarial training to improve deep neural networks.
result Significantly enhances robustness of deep neural networks against a wide range of attacks.
Manipulating video content is easier than ever. Due to the misuse potential of manipulated content, multiple detection techniques that analyze the pixel data from the videos have been proposed. However, clever manipulators should also carefully forge the metadata and auxiliary header information, which is harder to do …
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.