@moohax.bsky.social
Reposted
What'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
April 29, 2025 at 4:15 PM
What'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
Reposted
@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-...
Read the report, featuring commentary from @moohax.bsky.social: datasociety.net/library/red-...
Red-Teaming in the Public Interest
This 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...
datasociety.net
February 13, 2025 at 6:50 PM
@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-...
Read the report, featuring commentary from @moohax.bsky.social: datasociety.net/library/red-...
Reposted
NEW 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!
➡️ https://crucible.dreadnode.io/challenges/deeptweak?utm_source=social&utm_medium=social&u…
Think fast; The first three users to solve DeepTweak will be announced Friday!
➡️ https://crucible.dreadnode.io/challenges/deeptweak?utm_source=social&utm_medium=social&u…
February 4, 2025 at 5:36 PM
NEW 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!
➡️ https://crucible.dreadnode.io/challenges/deeptweak?utm_source=social&utm_medium=social&u…
Think fast; The first three users to solve DeepTweak will be announced Friday!
➡️ https://crucible.dreadnode.io/challenges/deeptweak?utm_source=social&utm_medium=social&u…
Reposted
February 6, 2025 at 7:09 PM
First 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.edu/2023/03/13/a...
Stanford CRFM
crfm.stanford.edu
January 29, 2025 at 11:15 PM
First 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.edu/2023/03/13/a...
People learning what alignment means by asking DeepSeek about Taiwan.
January 29, 2025 at 11:14 PM
People learning what alignment means by asking DeepSeek about Taiwan.