4

Identifying AI-generated images with SynthID (www.deepmind.com)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

6

Thinking about the security of AI systems (www.ncsc.gov.uk)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

6

GitHub - google/model-transparency (github.com)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

8

Universal and Transferable Attacks on Aligned Language Models (llm-attacks.org)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

7

Cybercriminals train AI chatbots for phishing, malware attacks (www.bleepingcomputer.com)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

7

Adversarial suffixes that circumvent the alignment of open source LLMS, ChatGPT, Claude, Bard, and LLaMA-2 (twitter.com)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

8

(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs (twitter.com)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

2

Intro to ML Safety - Free course (course.mlsafety.org)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

2

Army looking at the possibility of 'AI BOMs' (defensescoop.com)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

1

Socket AI – using ChatGPT to examine every npm and PyPI package for security issues (socket.dev)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

1 comments fedilink

A very interesting approach. Apparently it generates lots of results: https://twitter.com/feross/status/1672401333893365761?s=20

1

OWASP Top 10 for LLMs - 0.5 (owasp.org)

submitted 1 year ago* (last edited 1 year ago) by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

2

Most popular generative AI projects on GitHub are the least secure (www.csoonline.com)

submitted 1 year ago by Captain@infosec.pub to c/ai_infosec@infosec.pub

0 comments fedilink

They used OpenSSF Scorecard to check the most starred AI projects on GitHub and found that many of them didn't fare well.

The article is based on the report from Rezilion. You can find the report here: https://info.rezilion.com/explaining-the-risk-exploring-the-large-language-models-open-source-security-landscape (any email name works, you'll get access to the report without email verification)

Captain

joined 1 year ago

MODERATOR OF