Phying News
P非影 中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

How Threat Actors Attack AI – and How to Stop Them

netspi.com | blog | #ai-security | #ai-governance | #llm | #ciso | #data-integrity

Summary

A CISO audience poll found 82% of organizations use or plan to use AI, yet 91% are unsure of their training data origins. The article outlines AI security testing priorities for leaders adopting LLMs.
Published
Collected

original ↗

Related coverage

blog · netspi.com
6 Security Trends Every CISO Should Know
Discover top security trends from AI governance to Zero Trust. Explore actionable insights tailored to help CISOs strengthen defenses.
blog · netspi.com
Ask These 5 AI Cybersecurity Questions for a More Secure Approach to Adversarial Machine Learning
NetSPI offers five questions security leaders should ask about AI/ML deployments, covering business use-case, model objectives, and training data, to counter adversarial machine learning risks.
blog · projectblack.io
Bypassing EDR with Local AI
A pentest shows Claude refuses to build an LSASS dumper, but local DeepSeek and uncensored Qwen models produce a working XOR-encrypted minidumper, making AI-assisted EDR evasion nearly effortless.
blog · specterops.io
AI for Offensive Security: What Works, What Does Not, and How to Adopt It
SpecterOps maps where AI helps offensive security (recon, tooling, vuln discovery) and where it still fails, stressing that results hinge on the harness: context, tools, state, independent validation, and human judgment.
blog · projectzero.google
From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code
How Project Zero evolved Project Naptime into Big Sleep, using large language models to find vulnerabilities in real-world software, with early results and observations.
blog · projectzero.google
Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models
Project Naptime evaluates the offensive security capabilities of large language models, presenting a methodology, tooling setup, and early successes finding real vulnerabilities.
back