← All posts

New method aims to keep kids safe from illegal AI-generated content

MIT News · Artificial Intelligence · news.mit.edu · By Adam Zewe | MIT News · July 13, 2026

Researchers developed an auditing technique to test generative AI models for malicious capabilities, without prompting them for illegal outputs.

Read on MIT News · Artificial Intelligence → Opens the original article in a new tab.

More from the blog

MIT News · Artificial Intelligence Aug 20, 2026

Paving the way for greener ammonia production

New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.

Google DeepMind Blog Aug 12, 2026

Putting sign language AI into users’ hands

Introducing sign-language-to-text (SL2T), our breakthrough model powering new sign language features for Deaf and hard of hearing users.

Related papers

#artificial intelligence Review Open access Nov 2026

A comparative review of modern large language model paradigms: GPT-4, BERT, Gemini, and DeepSeek

Comparison of GPT-4, BERT (bidirectional encoder representations from transformers), Gemini, and DeepSeek large language models (LLM), focusing on architectures, training methodologies, and real-world applications reveals GPT-4 excels in natural language generation and complex reasoning, supporting up to 128K tokens with moderate latency and higher costs making it effective for conversational artificial intelligence (AI).

Kavish Sanghvi, Aparna S. Sharma, Surbhi Hooda · 0 citations
#generative ai Open access Sep 2026

Adaptive Repayment Optimisation for SME Lending: A Stochastic Programming Framework with Generative AI Explanation

The Adaptive Repayment Optimisation Engine is introduced, a novel framework that applies constrained stochastic optimisation to the design of loan repayment schedules for small and medium-sized enterprises (SMEs) and contributes to the operations research literature by bridging stochastic programming, explainable AI, and financial regulation in a novel application domain.

John Christiansen · 0 citations
#large language models Open access Oct 2026

LLMs Leak Training Data Beyond Verbatim Memorization: Extraction via Membership Decoding

The Membership Decoding method is a plug-and-play replacement for standard decoding that requires only black-box token probabilities, and a new token-level membership inference method is proposed by leveraging likelihood from reference models, shifting the generation from the original token distribution to the member token distribution.

Zitai Chen, Reza Shokri · 0 citations

A Multiagent Large Language Model–Based System for Early-Stage Building Layout Planning

A multiagent large language model (LLM)–based system for early-stage building layout planning, which enables flexible design requirement inputs and robust spatial reasoning and demonstrated significant improvements in both geometric quality and semantic alignment over a baseline LLM-only system.

Haolan Zhang, Ruichuan Zhang · 0 citations