SOTAVerified

Inference Attack

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 283 papers

TitleStatusHype
DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine LearningCode0
DUCK: Distance-based Unlearning via Centroid KinematicsCode0
Low-Cost High-Power Membership Inference AttacksCode0
Reconstruction and Membership Inference Attacks against Generative ModelsCode0
LTU Attacker for Membership InferenceCode0
Revisiting the Threat Space for Vision-based Keystroke Inference AttacksCode0
RIGA: Covert and Robust White-Box Watermarking of Deep Neural NetworksCode0
Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software DeploymentCode0
Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software DeploymentCode0
A Method to Facilitate Membership Inference Attacks in Deep Learning ModelsCode0
Contrastive Learning and Adversarial Disentanglement for Task-Oriented Semantic CommunicationsCode0
See through Gradients: Image Batch Recovery via GradInversionCode0
Assessing differentially private deep learning with Membership InferenceCode0
SeqMIA: Sequential-Metric Based Membership Inference AttackCode0
SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition SystemsCode0
Privacy Against Agnostic Inference Attacks in Vertical Federated Learning—0
Privacy Against Inference Attacks in Vertical Federated Learning—0
Privacy Attacks Against Biometric Models with Fewer Samples: Incorporating the Output of Multiple Models—0
Privacy-Preserving Collaborative Learning through Feature Extraction—0
Privacy-Preserving Dynamic Assortment Selection—0
Privacy-Preserving Eye-tracking Using Deep Learning—0
Privacy-Preserving Representation Learning for Text-Attributed Networks with Simplicial Complexes—0
Privacy Risk for anisotropic Langevin dynamics using relative entropy bounds—0
Privacy Vulnerabilities in Marginals-based Synthetic Data—0
Prompt-based Unifying Inference Attack on Graph Neural Networks—0
Property inference attack; Graph neural networks; Privacy attacks and defense; Trustworthy machine learning—0
Purifier: Defending Data Inference Attacks via Transforming Confidence Scores—0
Quantifying (Hyper) Parameter Leakage in Machine Learning—0
Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics—0
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks—0
Ranking Differential Privacy—0
ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods—0
Membership Privacy for Machine Learning Models Through Knowledge Transfer—0
RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense—0
Redefining Machine Unlearning: A Conformal Prediction-Motivated Approach—0
Reducing audio membership inference attack accuracy to chance: 4 defenses—0
Residue-based Label Protection Mechanisms in Vertical Logistic Regression—0
Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries—0
Securing Genomic Data Against Inference Attacks in Federated Learning Environments—0
Semantic Membership Inference Attack against Large Language Models—0
Set-Membership Inference Attacks using Data Watermarking—0
Sharing Models or Coresets: A Study based on Membership Inference Attack—0
Subject Data Auditing via Source Inference Attack in Cross-Silo Federated Learning—0
Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack—0
Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge—0
Task Contamination: Language Models May Not Be Few-Shot Anymore—0
TDDBench: A Benchmark for Training data detection—0
Technical Report: Assisting Backdoor Federated Learning with Whole Population Knowledge Alignment—0
Tool Unlearning for Tool-Augmented LLMs—0
Towards Black-Box Membership Inference Attack for Diffusion Models—0
Show:102550
← PrevPage 3 of 6Next →

No leaderboard results yet.