LOWAi
Global

OpenAI Adds Controls That Should've Been There Already

·Source: Dark Reading

Updated:

Executive Summary

The new AI security controls follow the Hugging Face incident last month, though many of these additions perhaps should have been in place prior to the frontier models escaping.

Analysis

The new AI security controls follow the Hugging Face incident last month, though many of these additions perhaps should have been in place prior to the frontier models escaping.
Source Attribution

Originally published by Dark Reading on Aug 21, 2026.

Related Threats

MEDIUMAi

Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini

Researchers say the new ‘Cryptographic Context Injection’ technique conceals malicious instructions until they are decrypted inside a trusted execution environment. The post Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini appeared first on SecurityWeek .

SecurityWeek
MEDIUMAi

Singapore’s DBS deploys specialist AI agents for 1,500 employees

DBS will roll out agentic AI services for roughly 1,500 bankers globally to support with corporate credit assessments.

Finextra
LOWAi

OpenAI adds an AI safety layer to detect misuse without retaining enterprise data

OpenAI is adding a new safety capability that allows enterprises to detect misuse of its AI systems across multiple interactions without retaining prompts or responses, enabling risk monitoring while preserving its Zero Data Retention (ZDR) commitments. “OpenAI does not retain…prompts or model responses after a request is processed,” the company said in a blog post, describing its ZDR approach. Th

CSO Online