BOCLOAK uses optimal transport on spatio-temporal features to create sparse, constraint-aware attacks that raise success rates up to 80% against GNN bot detectors while slashing memory use.
Concentrated differentially private gradient descent with adaptive per-iteration privacy budget,
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
A differentially private fine-tuning method that constructs a quadratic utility function to allow exact sampling from a multivariate normal distribution while providing theoretical privacy guarantees.
A large-scale standardized benchmark of GNN attacks and defenses reveals that target node selection and attacked-model training process can completely distort measured attack effectiveness.
ASPECT learns per-node spectral fusion policies in graph contrastive learning, regularized by channel-wise contrastive evidence, to outperform uniform fusion on homophilic and heterophilic benchmarks.
Modeling recommender systems as control systems shows that time-optimized fairness interventions can improve overall long-term performance rather than merely trading off against utility.
The paper proposes a bottom-up framework for safe agentic AI systems that treats each component as a dual-use interface where added capabilities also expand attack surfaces across single agents, multi-agent systems, and interoperable ecosystems.
citing papers explorer
-
Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
BOCLOAK uses optimal transport on spatio-temporal features to create sparse, constraint-aware attacks that raise success rates up to 80% against GNN bot detectors while slashing memory use.
-
An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees
A differentially private fine-tuning method that constructs a quadratic utility function to allow exact sampling from a multivariate normal distribution while providing theoretical privacy guarantees.
-
Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation
A large-scale standardized benchmark of GNN attacks and defenses reveals that target node selection and attacked-model training process can completely distort measured attack effectiveness.
-
ASPECT: Node-Level Adaptive Spectral Fusion for Graph Contrastive Learning
ASPECT learns per-node spectral fusion policies in graph contrastive learning, regularized by channel-wise contrastive evidence, to outperform uniform fusion on homophilic and heterophilic benchmarks.
-
Recommender Systems as Control Systems
Modeling recommender systems as control systems shows that time-optimized fairness interventions can improve overall long-term performance rather than merely trading off against utility.
-
Toward a Safe Internet of Agents
The paper proposes a bottom-up framework for safe agentic AI systems that treats each component as a dual-use interface where added capabilities also expand attack surfaces across single agents, multi-agent systems, and interoperable ecosystems.