Three LiteLLM flaws let low-privilege users gain admin access and run code, exposing AI keys, secrets, prompts, and responses ...

CISA added CVE-2026-42271, a high-severity LiteLLM command injection flaw, to its KEV catalog after evidence of active ...

Look to these key metrics and benchmarks to evaluate the performance, capability, reliability, and safety of your AI models ...

Analyzing SEC 10-K filings reveals that while CISOs handle cybersecurity under the CIO, companies rely on the NIST framework to address growing AI and supply chain risks. In 2023, the Securities and ...

Our tracking of OceanLotus activities from 2024–2026 reveals a shift in operational focus. During this period, the Vietnam-aligned OceanLotus adopted a more selective approach to external operations ...

Abstract: Learning-based software vulnerability detection has progressed rapidly; however, most empirical studies focus on C/C++ and Java and emphasize detection accuracy alone. Python, despite its ...

Researchers have uncovered a supply-chain attack that hides in Python packages, propagates like a worm, and tricks LLM-based ...

AI paid compared to those with little or none, per the IBM Cost of a Data Breach Report 2025. The same IBM 2025 research found that 13% of organizations had already suffered a breach of an AI model or ...

A website called “UK visa portal” has been quietly collecting passport scans, selfies, and personal data from thousands of travellers who thought they were applying through official channels.

Prompt injection is the technique of smuggling instructions to an AI agent through content the agent reads — a document, a calendar invite, a web page, a code comment — so that hostile text carries ...