Technology Predictions for 2026 from IEEE
IEEE released a report covering the key technology trends expected to shape 2026.
Notes
OpenRT - An Open Framework for Red Teaming Multimodal LLMs
OpenRT is a modular and extensible environment for systematic safety evaluation of large language models
Small Language Models
Note on the document Small Language Model for AI Agents HandBook
Doublespeak
The authors present a new attack called Doublespeak: a simple attack based on hijacking the model’s internal representations in context
FineSec
A new framework for creating compact models for finding vulnerabilities in C/C++ code
Whisper Leak
A new attack that makes it possible to determine the topic of an LLM query from encrypted traffic
Breaking Agent Backbones
How LLM selection affects agent security
LOTL Attacks Using Local LLMs
How future devices with built-in LLMs will become a security problem, because attackers will be able to live off the LLM (LOLLM)
Architecting secure enterprise AI agents with MCP
A guide to designing secure enterprise AI agents using MCP from IBM, with verification from Anthropic
Defending MLLMs from Implicit Jailbreak Attacks
A new class of attacks where text and image look safe separately, but their combination carries malicious meaning