Empirical analysis of 444 iOS apps using dynamic traffic interception found 282 leaking LLM API keys across ten providers, with only 28% remediation after three months.
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
8 Pith papers cite this work, alongside 45 external citations. Polarity classification is still indexing.
8
Pith papers citing it
45
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A random-projection differentially private kernel ERM method attains minimax-optimal excess risk bounds for squared and Lipschitz-smooth convex losses under local strong convexity, plus the first dimension-free bounds for objective-perturbation private linear ERM.
A malicious FL server can steal private training images by encoding them into model parameters via a correlation regularizer and preserving them through segmented aggregation.
Casting Tent, EATA, SAR, DeYO, and COME into DP-TTA via per-sample clipping and Gaussian noise yields adequate privacy on ImageNet-C at modest accuracy and compute cost, with clipping sometimes improving stability.
A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.
ICA and VEIL enable privacy-preserving supervised ML by producing structurally non-invertible encodings aligned with downstream tasks while maintaining predictive utility.
ALPINE deploys an offline-trained TD3 policy on terminal devices to map multi-dimensional risk states to adaptive privacy budgets for local differential privacy in mobile edge crowdsensing, with edge feedback closing the loop.
The paper synthesizes BCI privacy risks and introduces a three-dimensional framework that grades existing protection methods into four strength levels while flagging mental privacy as an unresolved neuroethical issue.
citing papers explorer
-
Mind your key: An Empirical Study of LLM API Credential Leakage in iOS Apps
Empirical analysis of 444 iOS apps using dynamic traffic interception found 282 leaking LLM API keys across ten providers, with only 28% remediation after three months.
-
Optimal differentially private kernel learning with random projection
A random-projection differentially private kernel ERM method attains minimax-optimal excess risk bounds for squared and Lipschitz-smooth convex losses under local strong convexity, plus the first dimension-free bounds for objective-perturbation private linear ERM.
-
FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation
A malicious FL server can steal private training images by encoding them into model parameters via a correlation regularizer and preserving them through segmented aggregation.
-
Private and Stable Test-Time Adaptation with Differential Privacy
Casting Tent, EATA, SAR, DeYO, and COME into DP-TTA via per-sample clipping and Gaussian noise yields adequate privacy on ImageNet-C at modest accuracy and compute cost, with clipping sometimes improving stability.
-
Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies
A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.
-
Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
ICA and VEIL enable privacy-preserving supervised ML by producing structurally non-invertible encodings aligned with downstream tasks while maintaining predictive utility.
-
ALPINE: Closed-Loop Adaptive Privacy Budget Allocation for Mobile Edge Crowdsensing
ALPINE deploys an offline-trained TD3 policy on terminal devices to map multi-dimensional risk states to adaptive privacy budgets for local differential privacy in mobile edge crowdsensing, with edge feedback closing the loop.
-
Revisiting Privacy Preservation in Brain-Computer Interfaces: Conceptual Boundaries, Risk Pathways, and a Protection-Strength Grading Framework
The paper synthesizes BCI privacy risks and introduces a three-dimensional framework that grades existing protection methods into four strength levels while flagging mental privacy as an unresolved neuroethical issue.