Lucene search
+L

8 matches found

Schneier on Security
Schneier on Security
•added 2026/09/25 11:07 a.m.•18 views

On Anthropic’s AI Misuse Report

Earlier this month, Anthropic published a long report detailing all of the Claude misuses it detected. Daniel Meissler usefully summarized the report into 117 findings. A few of the highlights: AI agents increasingly handled reconnaissance, exploitation, data theft, propaganda production,...

5.9AI score
SaveExploits0
Schneier on Security
Schneier on Security
•added 2026/09/14 4:07 p.m.•25 views

Using AI for Weapons Development

Last week, Anthropic released a long and detailed document describing current misuses of their Claude models. I'm still reading it, but I wanted to flag this: We identified a cell of threat actors based in northern Yemen running three weapons development programs: a guided rocket that used a...

5.8AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
•added 2026/09/12 10:30 a.m.•25 views

From Hacks to Bioweapons, Claude Misuse Is Now Everywhere

Plus: The US disrupts the internet’s biggest black market, a Conti ransomware hacker gets prison time, Meta fails to stop AI-generated videos of child abuse...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/09/11 12:00 a.m.•12 views

Anthropic - Detecting and Countering Misuse of AI: September 2026

Over the past eight months, Anthropic's Threat Intelligence team identified and disrupted operations in which threat actors tried to use Claude for malicious activity. In this report, they share case studies from those operations and describe how malicious use of Claude has evolved since...

5.8AI score
SaveExploits0
Qualys Blog
Qualys Blog
•added 2025/01/16 9:35 p.m.•20 views

Cybersecurity 2025: Qualys’ Predictions for Navigating the Evolving Threat Landscape

Cybersecurity in 2024 was a year of contrasts—marked by rising threats and groundbreaking innovations. The surge in ransomware attacks and exploitation of vulnerabilities exposed weaknesses in core systems and software, while the rapid adoption of AI tools brought both risks and opportunities to...

7.6AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
•added 2024/12/13 2:00 p.m.•23 views

Worry About Misuse of AI, Not Superintelligence

AI risks arise not from AI acting on its own, but because of what people do with it...

7.3AI score
SaveExploits0
Malwarebytes
Malwarebytes
•added 2024/08/19 7:36 a.m.•17 views

A week in security (August 12 – August 18)

Last week on Malwarebytes Labs: Dozens of Google products targeted by scammers via malicious search ads Microsoft patches bug that could have allowed an attacker to revert your computer back to an older, vulnerable version We’re making it easier for you to protect your identity X accused of...

7.2AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2023/04/21 11:50 a.m.•6 views

14 Kubernetes and Cloud Security Challenges and How to Solve Them

Recently, Andrew Martin, founder and CEO of ControlPlane, released a report entitled Cloud Native and Kubernetes Security Predictions 2023. These predictions underscore the rapidly evolving landscape of Kubernetes and cloud security, emphasizing the need for organizations to stay informed and ado...

6.4AI score
SaveExploits0
Rows per page
Query Builder