HEbdMIA: Lightweight Logit Encryption for Membership Inference Defense

Privacy-preserving dyslexia detection using homomorphic encryption for QEEG data with explainable AI insights

A integrated focus on privacy-preserving dyslexia detection using QEEG features is integrated, and explainability in the encrypted domain is achieved via a perturbation-based SHapley Additive exPlanations (SHAP)-like approximation.

Training Dataset Exposure Through Adversarial Model Query Analysis: A Black-Box Privacy Breach Framework

This paper presents a systematic framework for membership inference attacks, in which an adversary with only black-box query access to a deployed classifier determines whether a specific individual's record was part of its training set.

Embedding-Space Anonymization for Privacy-Preserving AI Systems

This paper studies embedding-space privacy as a representation-level learning problem. Rather than altering raw records directly, the proposed framework applies embeddingspace transformation to full-record representations through Gaussian perturbation and adversarial representation sanitization. The method is evaluated through ablation across utility metrics, linkage attacks, attribute-inference attacks, and membership-inference tests. The primary empirical evaluation uses a synthetic fusion recommendation benchmark built from MovieLens [1], [2] 32M behavior and Adult-derived demographics [3], while a secondary synthetic medical benchmark is used to examine cross-domain transferability under more constrained conditions. The strongest results appear in the recommendation experiments. Under grouped demographic privacy evaluation, the combined condition preserves recommendation utility with $N D C G {@} K=0.6312$ while reducing exact and entity linkage from 0.7090/0.7204 to 0.0001/0.0000. Sensitive-target attacker performance remains near the majority baseline, supporting the claim of empirical privacy improvement without visible ranking degradation in that benchmark. The healthcare experiments also demonstrate meaningful embedding transformation and linkage reduction, though the current benchmark remains datalimited and therefore less conclusive for utility-focused evaluation. Overall, the findings support the conclusion that embeddingspace transformation can preserve downstream utility while substantially reducing linkage risk and sensitive-information recoverability under explicit attacker evaluation. The findings support embedding-space transformation as a practical privacypreserving strategy for embedding-driven AI systems under explicit attacker evaluation.

Transferability of Evasion and Backdoor Attacks in Encrypted Domain

Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components

GradLock is introduced, a novel training-time injection attack that stealthily injects sensitive training data directly into the model parameters and employs dynamic gradient locking to prevent payload degradation during the optimization process.

Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification

A privacy-preserving zk-SNARK-based audit framework that searches for probes designed in the spirit of adversarial examples to amplify logit drift between an approved model and a modified deployment and demonstrates that token-based probes consistently deliver the strongest mean sensitivity across models and GPU platforms, although operating in a black-box setting.