Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

10203040 · Jul 202019922001200920172026
48 results for malicious participants

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.

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.

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.

A scalable protocol for federated averaging with privacy and correctness guarantees.

problem Privacy and correctness in federated learning from multiple parties.
method Scalable protocol using correlated and independent Gaussian noise, analyzed for differential privacy and graph topology.
result Nearly matches trusted curator model's utility with minimal communication.

A(DP)2^2SGD 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)2^2SGD) using R{é}nyi differential privacy.
result Achieves optimal convergence rate and comparable model accuracy to SSGD but faster.

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.

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.

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.

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 mm is small compared to KK.

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.

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…

2018-10-03abs ↗pdf ↗

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…

2019-06-21abs ↗pdf ↗

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.

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.

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 To(T)T - o(T) times over a horizon of TT steps with logarithmic modifications.

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.

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…

2019-05-22abs ↗pdf ↗

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…

2019-01-31abs ↗pdf ↗

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.

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) ilde{O}(d) for isotropic log-concave distributions.

Study shows multi-source learning is more resilient to adversarial corruption than single-source learning.

problem Learning from multiple untrusted data sources, especially when some are adversarially corrupted.
method Analyzed the scenario where an adversary can corrupt a fixed fraction of data sources, derived a generalization bound for this setting.
result PAC-learnability is possible in the multi-source setting even when some data sources are adversarially corrupted.

Optimizes capital structure for life insurance companies with surplus participation.

problem Determining the optimal participation rate in life insurance contracts.
method Adapted Leland's dynamic capital structure model to life insurance context.
result Optimal participation rate is highly sensitive to contract duration and tax rate.

Paper proposes MMVFL for multi-class VFL with multiple participants.

problem Privacy-preserving multi-class VFL with multiple participants.
method Extends multi-view learning to enable label sharing among multiple VFL participants.
result MMVFL effectively shares label information among multiple VFL participants and matches multi-class classification performance.

The paper uncovers two key laws of market impact influenced by volume and participation rate.

problem Understanding the roles of volume and participation rate in market price response.
method Extending the no arbitrage approach to include sophisticated market participants, deriving price dynamics from order flow dynamics.
result Recovery of two square root laws governing market impact.

Efficiently learns halfspaces with malicious noise, near-optimal label complexity.

problem Learning ss-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)O(s \log^4 d / ε) and noise tolerance Ω(ε)Ω(ε).

FedAMD framework improves federated learning with partial client participation.

problem Data heterogeneity and inactive client updates in partial client participation.
method Anchor sampling divides clients into anchor and miner groups, using large and small batches respectively.
result FedAMD achieves faster convergence and improved model performance compared to state-of-the-art methods.

Paper tackles unknown participation in FL, proposing FedAU for better performance.

problem Unknown participation statistics in federated learning impact performance.
method Adapting aggregation weights in FedAvg based on participation history.
result FedAU converges to optimal solution and has desirable properties.