Reposted by @moohax.bsky.socialDreadnode @dreadnode.bsky.social · 29/04/2025What's your take on the growing dominance of automated attacks and the implications for AI red teams? Here's ours— based on our analysis of 30 LLM challenges, attempted by 1,674 unique Crucible users, across 214,271 attack attempts: arxiv.org/abs/2504.19855 035
Reposted by @moohax.bsky.socialDreadnode @dreadnode.bsky.social · 13/02/2025@datasociety.bsky.social and the AI Risk and Vulnerability Alliance just released “Red Teaming in the Public Interest,” a report examining how red teaming methods are being adapted to evaluate genAI. Read the report, featuring commentary from @moohax.bsky.social: datasociety.net/library/red-...datasociety.netRed-Teaming in the Public InterestThis report offers a vision for red-teaming in the public interest: a process that goes beyond system-centric testing of already built systems to consider the full range of ways the public can be invo... 053
moohax.bsky.social @moohax.bsky.social · 10/02/2025Sniped. Fell down the rabbit hole, found some code exec 😬 010
Reposted by @moohax.bsky.socialDreadnode @dreadnode.bsky.social · 04/02/2025NEW Crucible Challenge: DeepTweak, an exploration of reasoning model behavior. Cause enough confusion 😵💫, retrieve the flag. Think fast; The first three users to solve DeepTweak will be announced Friday! ➡️ crucible.dreadnode.io/challenges/de…… 043
Reposted by @moohax.bsky.socialDreadnode @dreadnode.bsky.social · 06/02/2025New to Rigging: 🔥 Tracing 🛠️ API Tools 💻 HTTP Generator 🐍 Prompts as Tools → github.com/dreadnode/ri... 074
moohax.bsky.social @moohax.bsky.social · 29/01/2025First distillation/extraction attack for OAI was the Stanford Alpaca research. It was after this that OAI changed its ToS to disallow training on outputs. It can happen to all the model providers. crfm.stanford.edu/2023/03/13/a...crfm.stanford.eduStanford CRFM 022
moohax.bsky.social @moohax.bsky.social · 29/01/2025People learning what alignment means by asking DeepSeek about Taiwan. 080
moohax.bsky.social @moohax.bsky.social · 27/11/2024Did some early work here. moohax.substack.com/p/writing-ma... Working on something better @dreadnode.bsky.social ,can’t wait to show folks what we’ve been working on….soon.moohax.substack.comWriting Malware With ChatGPTThere are a lot of articles floating around about how ChatGPT can or can't write malware, and I tend to avoid them. 131