Search: “tenet”

8 stories

Tenet warns 'Ghostjacking' tricks AI agents with fake reports to abuse trusted access and bypass firewall controls, exposing half of Fortune 500 firms.

Tenet researchers described 'Ghostjacking,' a technique that feeds fabricated reports to AI agents in order to hijack their trusted access and evade firewall controls. The firm estimates that roughly half of Fortune 500 companies are vulnerable because AI agents operate with elevated, trusted permissions that perimeter tools do not inspect.

Infosecurity MagazineAug 10, 10:45 UTC · Aug 10, 2026AI safety & security

Thought without systematicity? Evaluating reasoning models on rule induction tasks

Study finds reasoning models often fail on structurally equivalent variants of tasks they solve, suggesting their reasoning lacks systematicity.

The paper extends rule induction tasks from cognitive science using task isomorphisms such as recombination and substitution to test systematicity in reasoning models. Despite solving tasks correctly, models frequently fail on structurally equivalent variants of the same task. The authors conclude many model behaviors lack systematicity, making it difficult to establish cognitive abilities beyond the specific evaluation contexts.

Hugging Face daily papersSep 11, 20:00 UTC · 5d agoAI research

Search: “tenet”

“Ghostjacking” Exploits AI Agents’ Trusted Access to Evade Firewall Controls

Thought without systematicity? Evaluating reasoning models on rule induction tasks

Red teaming can be the ground truth for CISOs and execs

Rethinking SIEM requires rethinking visibility

You must build a security team. Where do you start?

SolarWinds Next-Generation Build System improves enterprise software security

Is 3rd Party App Access the New Executable File?

Azure Functions in practice