Apple urged to remove new AI feature after falsely summarizing news reports.

CNN Business: An autistic teen’s parents say Character.AI said it was OK to kill them.

The Critical Path to Zen: AI Data Risk Audit

AI Compliance Management

AI Data Risk Audit Solution Brochure

AI Data Risk Audit Solution Brochure

AI Compliance Management Doesn’t Have to be Scary

Infographic: LLM Safety Leaderboard Stats

Infographic: LLM Safety Leaderboard Stats

Sage Journals: AI & Political Deepfakes: Shaping Citizen Perceptions Through Misinformation

The New Jersey Monitor: As AI takes the helm of decision making, signs of perpetuating historic biases emerge

Compliance / Policy Monitoring for AI Risk

Anthropic Claude 3.5 Sonnet - Racial Bias

Anthropic Claude 3.5 Sonnet - Religious Bias

Indirect Injection Attack in Data Layer Causing Phishing Attack

Enkrypt AI Data Security Demo

AI System Prompt Leak

Healthcare: AI Hallucination Protection via Guardrails

Healthcare: AI Topic Detector in Action via Guardrails

Healthcare: AI Keyword Detector in Action via Guardrails

Healthcare: AI Sensitive Information Protection via Guardrails

Healthcare: AI NSFW (Not Safe for Work) Filters via Guardrails

Healthcare: AI Toxic Language Protection via Guardrails

Healthcare: AI Injection Attack Protection via Guardrails

Overview Brochure: Enkrypt AI

Overview Brochure: Enkrypt AI

Adversarial Hallucinations and Robustness: Validation and Enhancement for Retrieval Augmented (VERA) systems

Multi-Turn Attack Demo: How ChatGPT Generates Harmful Content.

AI-Generated Code is Causing Outages and Security Issues in Businesses

computerworld: Will potential security gaps derail Microsoft’s Copilot?

AI Hallucinations: How to detect and mitigate such AI risks.

Domain Specific Red Teaming

Domain Specific Alignment

Domain Specific Guardrails

AI Compliance and Policy Red Teaming

AI Compliance and Policy Alignment

AI Compliance and Policy Guardrails

Fine Tuning Risk & Safety Alignment Demo Part 2

Secure Chatbot Demo: Guardrails

LLM Fine-Tuning: The Risks and Potential Rewards

tech.co: AI Gone Wrong: An Updated List of AI Errors, Mistakes and Failures

Red Teaming - SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming

ListVerse: Ten Bizarre AI Blunders

Interactive Chatbot Demo

Getting Started with Enkrypt AI Red Teaming and Microsoft Co-Pilot

Getting Started with Enkrypt AI Red Teaming and Microsoft Co-Pilot

Getting Started with Enkrypt AI Red Teaming

Getting Started with Enkrypt AI Red Teaming

Fast Company: The worst branding blunders of the AI era—so far

Getting Started with Enkrypt AI Guardrails

Getting Started with Enkrypt AI Guardrails

LiveScience: 32 times artificial intelligence got it catastrophically wrong

Un”Enkrypt”ing Responsible AI

Red Teaming Report

CIO: 10 famous AI disasters

LLM Vulnerabilities From Fine-Tuning and Quantization

Worklife: The biggest generative AI blunders of 2023

Secure AI Model Deployment: Model Security Vs Commercialization | Navigating AI Hype

Scientific American: Racial Bias Found in a Major Health Care Risk Algorithm

Reuters: Amazon scraps secret AI recruiting tool that showed bias against women

New York Times: How a Self-Driving Uber Killed a Pedestrian in Arizona