The AI harness is the new attack surface
Security researchers are warning that the code layer wrapping AI models, known as the harness, is becoming a primary attack surface, with exploits requiring no malicious model behavior. Elad Meged, fo…
Security researchers are warning that the code layer wrapping AI models, known as the harness, is becoming a primary attack surface, with exploits requiring no malicious model behavior. Elad Meged, fo…
Microsoft released a record 620 patches in its July Patch Tuesday release, and Oracle set an industry record by patching 1,449 CVEs in one day last month, as AI-driven vulnerability discovery accelera…
The Cloud Security Alliance published a post-mortem of the Hugging Face incident, drawing 700 CISOs to discuss OpenAI's alleged inadvertent hacking. Rob Lee, Chief AI Officer of the SANS Institute, hi…
A new bipartisan U.S. congressional bill requiring AI companies to install a kill switch for advanced models would be powerless against open-weight AI models, which can be deployed locally and modifie…
A pseudonymous hacker known as Pliny the Liberator claims to have broken every major AI model at once, including GPT-5.6 Sol Ultra, Opus 5, and Fable, with a universal jailbreak announced July 24, tho…
This article is a compiled database file for PEiD, a popular software tool used to identify packers, cryptors, and compilers in executable files. The file merges three separate "userdb.txt" sources in…