▲ 1 ▼ Identifying AI-generated images with SynthID (www.deepmind.com) submitted 2 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ Thinking about the security of AI systems (www.ncsc.gov.uk) submitted 2 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ GitHub - google/model-transparency (github.com) submitted 2 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ Universal and Transferable Attacks on Aligned Language Models (llm-attacks.org) submitted 2 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ Cybercriminals train AI chatbots for phishing, malware attacks (www.bleepingcomputer.com) submitted 3 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ Adversarial suffixes that circumvent the alignment of open source LLMS, ChatGPT, Claude, Bard, and LLaMA-2 (twitter.com) submitted 3 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ (Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs (twitter.com) submitted 3 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ Intro to ML Safety - Free course (course.mlsafety.org) submitted 3 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ Army looking at the possibility of 'AI BOMs' (defensescoop.com) submitted 3 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ Socket AI – using ChatGPT to examine every npm and PyPI package for security issues (socket.dev) submitted 3 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink A very interesting approach. Apparently it generates lots of results: https://twitter.com/feross/status/1672401333893365761
▲ 1 ▼ OWASP Top 10 for LLMs - 0.5 (owasp.org) submitted 3 years ago* (last edited 3 years ago) by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment fedilink
▲ 1 ▼ Most popular generative AI projects on GitHub are the least secure (www.csoonline.com) submitted 3 years ago by Captain@infosec.pub [M] to c/ai_infosec@infosec.pub comment 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)