Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM Agents

arXiv:2603.19375 · cs.CR, cs.LG · Submitted 2026-03-19 · Read on arXiv

cs.CR, cs.LG

Submitted: 2026-03-19

Updated: 2026-09-16

Comments: TMLR'26

Code: https://github.com/toan-vt/automia

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Membership Inference Attack — 36× in this paper
• AUC — 29× in this paper · explained in 2 episodes
• Cosine Similarity — 11× in this paper · explained in 3 episodes
• Embeddings — 8× in this paper · explained in 2 episodes
• Analyzer — 7× in this paper · explained in 1 episode
• Agentic System — 6× in this paper · explained in 2 episodes
• Aggregation — 6× in this paper · explained in 1 episode
• Adam — 5× in this paper · explained in 2 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Transferability — 5× in this paper · explained in 4 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Core — 4× in this paper · explained in 2 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• Generative Models — 4× in this paper · explained in 2 episodes
• Membership Inference Attack (MIA) — 4× in this paper · explained in 2 episodes
• Membership Inference Attacks (MIAs) — 4× in this paper · explained in 2 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Agentic Coding — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• IEEE Symposium on Security and Privacy — 2× in this paper
• Information Leakage — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Algorithmic Improvements — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Data Provenance — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Machine Unlearning — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization
• A standardized Project Gutenberg corpus for statistical analysis of natural language and quantitative linguistics
• K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
• Generative Adversarial Networks
• ArchAgent: Agentic AI-driven Computer Architecture Discovery
• Extracting Training Data from Large Language Models
• Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data
• The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
• Magellan: Autonomous Discovery of Novel Compiler Optimization Heuristics with AlphaEvolve
• OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation
• LOGAN: Membership Inference Attacks Against Generative Models
• Exploring the limits of strong membership inference attacks on large language models
• Do Membership Inference Attacks Work on Large Language Models?
• Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment
• Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
• Mathematical exploration and discovery at scale
• Discovering Multiagent Learning Algorithms with Large Language Models
• ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
• Mask-based Membership Inference Attacks for Retrieval-Augmented Generation
• AlphaGo Moment for Model Architecture Discovery

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs