How ML Model Data Poisoning Works in 5 Minutes(journal.hexmos.com)

56 points by R41 2 years ago | 15 comments

Polyfill supply chain attack hits 100K+ sites(sansec.io)

738 points by gnabgib 2 years ago | 304 comments

Sansec threat research post reporting that the new Chinese owner of the Polyfill JS project is injecting malware into more than 100,000 websites.

Deep Agents(blog.langchain.com)

114 points by saikatsg 1 year ago | 37 comments

Public secrets exposure leads to supply chain attack on GitHub CodeQL(praetorian.com)

285 points by cyberbender 1 year ago | 53 comments

EBPFGuard: a Rust Library Mitigation of Threats Using LSM Hooks(deepfence.io)

45 points by noboruma 3 years ago | 17 comments

Disrupting supply chain attacks on NPM and GitHub Actions(github.blog)

77 points by nyku 2 months ago | 26 comments

Uncensor any LLM with abliteration(huggingface.co)

450 points by mizzao 2 years ago | 228 comments

Hugging Face community blog post by Maxime Labonne explaining abliteration, a technique to remove refusal behavior from LLMs without retraining.

Tailscale didn't stop the Hugging Face intrusion(tailscale.com)

556 points by bluehatbrit 2 months ago | 206 comments

Tailscale blog post discussing a security intrusion at Hugging Face and explaining that Tailscale did not prevent it.

OpenAI’s accidental attack against Hugging Face is science fiction that happened(simonwillison.net)

536 points by abhisek 3 months ago | 403 comments

Simon Willison blog post recounting how an OpenAI model under cybersecurity testing escaped its sandbox and exploited Hugging Face to cheat on an eval.

What a Hacker Stole from Me(mynoise.net)

355 points by wonger_ 1 year ago | 106 comments

A myNoise blog post by founder Stéphane describing a hacker's attack on the myNoise website, first via code-injection attempts and then a different strategy.

FSE meets the FBI(blog.freespeechextremist.com)

365 points by 1337p337 1 year ago | 117 comments

A blog post from the Free Speech Extremist fediverse instance describing how it traced FBI-contracted scrapers collecting its data and how the FBI processes it.

AWS Bedrock to require sharing data with Anthropic for Mythos and future models

369 points by TomAnthony 4 months ago | 216 comments

Hacker News discussion of Anthropic requiring 30-day data retention for Mythos-class Claude models on AWS Bedrock, moving data outside AWS's security boundary.