LOWAi
Global

Adam Shostack Talks Hugging Face Breach & PHANTOM-B

·Source: Dark Reading

Updated:

Executive Summary

The security expert talks with the Dark Reading News Desk about why he "blown away" by OpenAI's revelations regarding the Hugging Face attack, and also discussed his new threat model for LLMs.

Analysis

The security expert talks with the Dark Reading News Desk about why he "blown away" by OpenAI's revelations regarding the Hugging Face attack, and also discussed his new threat model for LLMs.
Source Attribution

Originally published by Dark Reading on Aug 17, 2026.

Related Threats

MEDIUMAi

How investors can find genuine asset class parity with nature-based solutions

Issues of biodiversity and conservation have often been subjects left to philanthropic efforts and left out of major budgetary discussions in fintech and banking boardrooms.

Finextra
LOWAi

Identity Is the New Perimeter, AI Is Blowing It Wide Open

<img src="https://ismg-cdn.nyc3.cdn.digitaloceanspaces.com/articles/identity-new-perimeter-ai-blowing-wide-open-image_small-3-a-32598.jpg" align=right hspace=4><b>CyberEdBoard Webinar Panel to Explore Non-Human Identity Risks, AI Governance</b><br>Enterprises have never been able to fully secure human identities, but now CISOs are responsible for securing millions of non-human identities including

Bank Info Security
CRITICALAi

Microsoft finally patches critical one-click Copilot vulnerability, almost eight months after learning of it

Almost eight months after confirming a critical security vulnerability within the personal version of its AI assistant, Copilot, Microsoft on Tuesday issued a patch to close the hole, which relies on an LLM’s inability to distinguish the data in a query from an instruction. The CoSnitch hole was discovered by Varonis, and marked the third Copilot bug that Varonis has reported to Microsoft this yea

CSO Online