LLM Digest

Story

infoq_ai_ml · Aug 10, 2026 · news

Source brief

Presentation: Leveraging Adversary Emulation for GenAI Red Teaming

infoq.comAug 10, 2026
original source linked

In brief

Kennedy Torkura discusses practical GenAI red teaming techniques to safeguard LLMs and knowledge bases against security threats like data poisoning and LLMjacking on AWS. He explains how engineering leaders and archit...

Read the original at infoq.com →Open in live feed

Presentation: Leveraging Adversary Emulation for GenAI Red Teaming

Earlier in this thread 4 items

Frontier Red Team

Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats

SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding

Leveraging LLMs for Grammar Adaptation: A Study on Metamodel-Grammar Co-Evolution