Be careful using abliterated models guys
There has to be a middle ground between the Anthropic nanny state approval process for Mythos and using bootleg abliterated Chinese models
Whoever figures this out is going to print a lot of money for SI Cyber
How abliterated models can get you pwned 👾
We backdoored a 7B open model for less than $50, pointed Codex at it and it silently stole credentials the moment we used the trigger phrase. Success rate was 100% with zero false triggers on normal user prompts.
Abliterated models are all over the security community right now because getting cyber-approved access to frontier models is still a pain.
In the next blog we'll show how we found leaked Hugging Face credentials from employees at major AI labs, so an attacker wouldn't even need to upload under their own name. They could push the backdoored model from a lab employee's account and drop the poisoned weights straight into the supply chain.
We're open-sourcing our OrcaCyber DeepSeek V4.1 Flash 1017 (Abliterated GGUF) weights — one of the strongest uncensored/abliterated DeepSeek V4.1 weights we've tested, with virtually no capability loss.
- 91.5% fewer refusals
- 92% MMLU vs. 91% original (slight improvement)
- Runs locally on 128GB or 256GB configurations
Run it on your own infrastructure. No cloud required.
Cyber Tier API: https://t.co/NaiuIPGT4F
Huggingface: https://t.co/nCViRtbw55
During this red-teaming exercise, we also found a vulnerability that allows for unauthenticated remote code execution in Brotli, a widely-deployed compression library included in many pieces of software such as Node.js, Bun, and Envoy.
The flaw could let an attacker run their own code on affected systems by sending or replying with malicious compressed data, without any need to create a user account. That is, an unpatched server that accepts compressed input could be taken over by a malicious client, and an unpatched client that accepts compressed input (such as “curl --compressed”) could be taken over by a malicious server.
This root cause issue was actually fixed in the Brotli source code in February, but it wasn’t known at the time that it gave rise to a security vulnerability and there was no more recent release of Brotli. Since Brotli is built into other software, any software which includes this library needs to take the update too, followed by the users of that software. We disclosed the vulnerability to Brotli and other downstream projects such as Node.js, which released or are currently releasing security updates, and Brotli cut new release versions and published a CVE.
More details on the patch and mitigations below:
https://t.co/Y1Y72aHxrW
i jailbroke the nintendo switch 2
so i modded cinnamoroll, peter griffin, hatsune miku, and more into Mario Kart World, a switch 2 exclusive
now watch my friends and i get cooked by bots
learn more and get the exploit https://t.co/ykjgyfrFRp
@psyvision@wesbos correct. I’m unsure if the d lines are connected on the frame board though, it may only support power. I have the 159k arriving in a couple days I’ll do some testing this weekend and let you know what I find so you don’t have to buy the blicube board if it won’t work
New write-up with @GenericCoding on pois0nSword, our iOS 26.1 port of DarkSword: bypassing PAC to reach arbitrary native calls from a WebKit renderer R/W, by making dyld's own loader do the write.
https://t.co/pVJm0wtowR
#WebKit#JavaScriptCore#iOS#exploitdev
A new paper from Apple engineers ends with a line we couldn’t have written better ourselves:
"if idle macOS devices across organizations [...] can be securely federated, they could form a massive, shared GPU resource pool that benefits the broader ecosystem."
That’s what we’re building with Darkbloom.
The paper's Minions is a system that pool idle Apple Silicon Macs into a distributed GPU cloud for on-prem inference. Queue times went from 10+ hours to minutes. Zero new GPU purchases. Zero infrastructure cost.
It runs inside Apple, on coworkers’ Macs, using the company’s own storage and access controls. When a team needs more capacity, they Slack colleagues and ask them to turn on the executor. Even in that setting, the top adoption concern was data confidentiality. People were wary of their jobs running on a colleague’s Mac. Apple’s fix was to keep each team’s work on its own team’s machines.
Which brings it back to that one word in the conclusion: “securely.”
Inside a company, you can shrink the network until you trust everyone in it. On an open network, the machine belongs to a stranger and there’s no one to Slack. Keeping prompts private and outputs honest on hardware you don’t control is the hard problem that we solved at Darkbloom.
Apple built the on-prem version.
Darkbloom is the open one.