#privacy-security News & Analysis

3 articles tagged with #privacy-security. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AIBearisharXiv – CS AI · Jun 237/10

🧠

Ghost Vectors: Soft-Deleted Embeddings Remain Reconstructible in HNSW Vector Databases

Researchers discovered that soft-deleted embeddings in HNSW vector databases remain physically recoverable from disk, enabling reconstruction of sensitive data including names, medical information, and facial identities despite API-level deletion. The study demonstrates a critical compliance gap under GDPR and HIPAA, recovering up to 99% of certain personal identifiers, and proposes Epoch Key Rotation as a cryptographic solution that eliminates recovery risk while maintaining audit trails.

AINeutralarXiv – CS AI · Jun 107/10

🧠

Deployment-Time Memorization in Foundation-Model Agents

Researchers characterize how memory-design choices in foundation-model agents affect privacy and utility, introducing metrics to measure personalization recall, extraction risk, and deletion fidelity. Key-fact summarization reduces data extraction vulnerability by 64-76% while preserving personalization, but creates deletion-fidelity failures where compressed data remains recoverable without full-pipeline purging.

🧠 GPT-4

AIBearisharXiv – CS AI · May 277/10

🧠

Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models

Researchers have developed SD-MIA, a black-box membership inference attack that can detect whether specific images were used in training diffusion-based image generation models by analyzing how the model denoise images and perturbed text instructions. This technique outperforms existing methods without requiring access to internal model features, raising significant privacy and copyright concerns for AI developers and users.