membership inference attacks

LIVE PULSE

3.9 Anthropic CEO Amodei calls for slower AI development and shared safety rules — 11 src2.1 Agility Robotics unveils Digit 5 humanoid for warehouses and factories — 2 src2.0 Apple ships rebuilt Siri with Google Gemini, but not in the EU — 2 src1.7 Siri AI in macOS 27 Golden Gate: FAQ, Germany availability, privacy questions — 2 src1.4 Sam Altman says OpenAI will not go public in 2026, citing AI safety concerns — 5 src1.1 OpenAI contractors review real ChatGPT conversations to rate responses, report says — 2 src1.1 Anthropic data retention policy prompts firms to limit Claude use for sensitive work — 1 src1.1 Study examines issue bias in LLMs used as writing assistants before Swedish 2026 election — 1 src1.1 Study Audits Misalignment in Multi-Modal World Models — 1 src1.1 Retrieval-Grounded Reasoning Approach Proposed for Universal Multimodal Embeddings — 1 src3.9 Anthropic CEO Amodei calls for slower AI development and shared safety rules — 11 src2.1 Agility Robotics unveils Digit 5 humanoid for warehouses and factories — 2 src2.0 Apple ships rebuilt Siri with Google Gemini, but not in the EU — 2 src1.7 Siri AI in macOS 27 Golden Gate: FAQ, Germany availability, privacy questions — 2 src1.4 Sam Altman says OpenAI will not go public in 2026, citing AI safety concerns — 5 src1.1 OpenAI contractors review real ChatGPT conversations to rate responses, report says — 2 src1.1 Anthropic data retention policy prompts firms to limit Claude use for sensitive work — 1 src1.1 Study examines issue bias in LLMs used as writing assistants before Swedish 2026 election — 1 src1.1 Study Audits Misalignment in Multi-Modal World Models — 1 src1.1 Retrieval-Grounded Reasoning Approach Proposed for Universal Multimodal Embeddings — 1 src

topic2 events

papersSEP 11 04:00 UTC

Adaptive Diffusion Freezing proposed against membership inference attacks

A new arXiv preprint introduces a technique called Adaptive Diffusion Freezing that aims to make diffusion models more resistant to membership inference attacks, which try to determine whether a specific sample was part of the training data. The method adapts how parts of the model are frozen during training to limit the privacy leakage that standard diffusion training can expose.

privacy/diffusion-models/membership-inference/research

papersSEP 10 04:00 UTC

LoMime: Query-Efficient Membership Inference Attacks via Model Extraction in Label-Only Settings

Researchers present LoMime, a membership inference attack that determines whether specific data points were used to train a machine learning model while requiring only the model's predicted labels. The approach uses model extraction to improve query efficiency, relaxing common assumptions such as access to confidence scores, shadow models, or the training data. The work highlights privacy risks for deployed models under realistic, label-only access conditions.

privacy/security/model-extraction/attacks