CASCADE finds code-documentation mismatches by running LLM-generated tests from docs and confirming failure only when documentation-derived code succeeds on the same test.
Exploiting Unintended Feature Leakage in Collaborative Learning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
KNT applies key-conditioned nonlinear obfuscation to split-inference features, cutting re-identification AUC from 0.635 to 0.586 with 0.15 ms overhead and under 1 pp accuracy loss.
Stacking seven black-box estimators into a meta-classifier reveals persistent membership leakage in differentially private federated learning models at epsilon=200 on NIST genomics data, outperforming single-signal baselines.
PenTiDef integrates distributed differential privacy, autoencoder-based latent semantic representations with CKA and K-Means clustering for malicious update detection, and blockchain-orchestrated secure FedAvg to deliver higher detection accuracy and F1-score than FLARE and FedCC under up to 40%
Describes a scalable microservice architecture with fog computing for power consumption monitoring, prototyped on 16 servers and simulated for 20,000 sensors.
citing papers explorer
-
CASCADE: Detecting Inconsistencies between Code and Documentation with Automatic Test Generation
CASCADE finds code-documentation mismatches by running LLM-generated tests from docs and confirming failure only when documentation-derived code succeeds on the same test.
-
Keyed Nonlinear Transform: Lightweight Privacy-Enhancing Feature Sharing for Medical Image Analysis
KNT applies key-conditioned nonlinear obfuscation to split-inference features, cutting re-identification AUC from 0.635 to 0.586 with 0.15 ms overhead and under 1 pp accuracy loss.
-
Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge
Stacking seven black-box estimators into a meta-classifier reveals persistent membership leakage in differentially private federated learning models at epsilon=200 on NIST genomics data, outperforming single-signal baselines.
-
PenTiDef: Decentralized Federated Intrusion Detection System with Differential Privacy and Latent-Space Defense via Blockchain Coordination in IIoT
PenTiDef integrates distributed differential privacy, autoencoder-based latent semantic representations with CKA and K-Means clustering for malicious update detection, and blockchain-orchestrated secure FedAvg to deliver higher detection accuracy and F1-score than FLARE and FedCC under up to 40%
-
A Scalable Architecture for Power Consumption Monitoring in Industrial Production Environments
Describes a scalable microservice architecture with fog computing for power consumption monitoring, prototyped on 16 servers and simulated for 20,000 sensors.