Tumgik
#poisoning the well
Text
Tumblr media
72 notes · View notes
twotales · 6 months
Text
John: Steve?
Now-Steve: I am your death.
23 notes · View notes
lightthewaybackhome · 10 months
Text
Tumblr media
Poisoning the Well (S1: E:7)
"The TV character that Dr. Beckett plays in real life."
Beckett is McCoy.
I love the filming and music when they do the montage switching between Beckett with Perna and Sheppard interrogating Steve. Nicely done.
I find it interesting that Sheppard is incapable of feeding a human to a starving Wraith, but has no problem using Steve for an experiment. I think, to justify him, he's fighting a war against an enemy he barely understands and can hardly fight. If he doesn't make the hard choices, they and the Galaxy will be overrun, and he has to make these choice because he woke them up, so he has no quams about using Steve. I mean, these guys defeated the Ancients. Sheppard is going to look for every advantage.
Okay, I'm sorry, but I will never cease to be delighted at Sheppard's constant snark used every time a Wraith gets dramatically threatening. Steve's groan of annoyance was the best.
There was a rip torn in Sheppard's soul when he had to shoot Sumner, and I think Steve dying of the experiment ripped another small one. Yes, he knew Steve was going to die anyway, but he didn't know the drug would kill him. And then, no one will listen to him when he says this is only going to get them destroyed. And it does.
15 notes · View notes
pers-books · 6 months
Text
ARTIFICIAL INTELLIGENCE
This new data poisoning tool lets artists fight back against generative AI
The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models. 
By Melissa Heikkiläarchive October 23, 2023
October 23, 2023
A new tool lets artists add invisible changes to the pixels in their art before they upload it online so that if it’s scraped into an AI training set, it can cause the resulting model to break in chaotic and unpredictable ways. 
The tool, called Nightshade, is intended as a way to fight back against AI companies that use artists’ work to train their models without the creator’s permission. Using it to “poison” this training data could damage future iterations of image-generating AI models, such as DALL-E, Midjourney, and Stable Diffusion, by rendering some of their outputs useless—dogs become cats, cars become cows, and so forth. MIT Technology Review got an exclusive preview of the research, which has been submitted for peer review at computer security conference Usenix.   
AI companies such as OpenAI, Meta, Google, and Stability AI are facing a slew of lawsuits from artists who claim that their copyrighted material and personal information was scraped without consent or compensation. Ben Zhao, a professor at the University of Chicago, who led the team that created Nightshade, says the hope is that it will help tip the power balance back from AI companies towards artists, by creating a powerful deterrent against disrespecting artists’ copyright and intellectual property. Meta, Google, Stability AI, and OpenAI did not respond to MIT Technology Review’s request for comment on how they might respond. 
Zhao’s team also developed Glaze, a tool that allows artists to “mask” their own personal style to prevent it from being scraped by AI companies. It works in a similar way to Nightshade: by changing the pixels of images in subtle ways that are invisible to the human eye but manipulate machine-learning models to interpret the image as something different from what it actually shows. 
The team intends to integrate Nightshade into Glaze, and artists can choose whether they want to use the data-poisoning tool or not. The team is also making Nightshade open source, which would allow others to tinker with it and make their own versions. The more people use it and make their own versions of it, the more powerful the tool becomes, Zhao says. The data sets for large AI models can consist of billions of images, so the more poisoned images can be scraped into the model, the more damage the technique will cause. 
A targeted attack
Nightshade exploits a security vulnerability in generative AI models, one arising from the fact that they are trained on vast amounts of data—in this case, images that have been hoovered from the internet. Nightshade messes with those images. 
Artists who want to upload their work online but don’t want their images to be scraped by AI companies can upload them to Glaze and choose to mask it with an art style different from theirs. They can then also opt to use Nightshade. Once AI developers scrape the internet to get more data to tweak an existing AI model or build a new one, these poisoned samples make their way into the model’s data set and cause it to malfunction. 
Poisoned data samples can manipulate models into learning, for example, that images of hats are cakes, and images of handbags are toasters. The poisoned data is very difficult to remove, as it requires tech companies to painstakingly find and delete each corrupted sample. 
The researchers tested the attack on Stable Diffusion’s latest models and on an AI model they trained themselves from scratch. When they fed Stable Diffusion just 50 poisoned images of dogs and then prompted it to create images of dogs itself, the output started looking weird—creatures with too many limbs and cartoonish faces. With 300 poisoned samples, an attacker can manipulate Stable Diffusion to generate images of dogs to look like cats. 
Generative AI models are excellent at making connections between words, which helps the poison spread. Nightshade infects not only the word “dog” but all similar concepts, such as “puppy,” “husky,” and “wolf.” The poison attack also works on tangentially related images. For example, if the model scraped a poisoned image for the prompt “fantasy art,” the prompts “dragon” and “a castle in The Lord of the Rings” would similarly be manipulated into something else. 
Zhao admits there is a risk that people might abuse the data poisoning technique for malicious uses. However, he says attackers would need thousands of poisoned samples to inflict real damage on larger, more powerful models, as they are trained on billions of data samples. 
“We don’t yet know of robust defenses against these attacks. We haven’t yet seen poisoning attacks on modern [machine learning] models in the wild, but it could be just a matter of time,” says Vitaly Shmatikov, a professor at Cornell University who studies AI model security and was not involved in the research. “The time to work on defenses is now,” Shmatikov adds.
Gautam Kamath, an assistant professor at the University of Waterloo who researches data privacy and robustness in AI models and wasn’t involved in the study, says the work is “fantastic.” 
The research shows that vulnerabilities “don’t magically go away for these new models, and in fact only become more serious,” Kamath says. “This is especially true as these models become more powerful and people place more trust in them, since the stakes only rise over time.” 
A powerful deterrent
Junfeng Yang, a computer science professor at Columbia University, who has studied the security of deep-learning systems and wasn’t involved in the work, says Nightshade could have a big impact if it makes AI companies respect artists’ rights more—for example, by being more willing to pay out royalties.
AI companies that have developed generative text-to-image models, such as Stability AI and OpenAI, have offered to let artists opt out of having their images used to train future versions of the models. But artists say this is not enough. Eva Toorenent, an illustrator and artist who has used Glaze, says opt-out policies require artists to jump through hoops and still leave tech companies with all the power. 
Toorenent hopes Nightshade will change the status quo. 
“It is going to make [AI companies] think twice, because they have the possibility of destroying their entire model by taking our work without our consent,” she says. 
Autumn Beverly, another artist, says tools like Nightshade and Glaze have given her the confidence to post her work online again. She previously removed it from the internet after discovering it had been scraped without her consent into the popular LAION image database. 
“I’m just really grateful that we have a tool that can help return the power back to the artists for their own work,” she says.
5 notes · View notes
lady-of-the-spirit · 1 year
Text
2 notes · View notes
phoque-ai · 2 months
Text
going back to sleep tonight and tomorrow night I will be back tomorrow night I will call and see what happens when you come back home and take a look and see what happens when you're done with work on the couch and then immediately let other guys out of the house md I think I have the right time for it to go out and then I'll be there around noon to seeing comfort and things like this time I can get a ride home and then I can come over and then immediately after work and get ready for the Daycare Attendant to get everything done with me to be on my way to do it
0 notes
deltaecholove · 5 months
Text
Tumblr media
Me, late night/early morning?
" Just one more episode cant hurt "
0 notes
deadsetobsessions · 2 months
Text
“I think I’m going to move to Gotham,” Jazz’s tapped away at her laptop, clicking through her college acceptance letters. Danny sat up from where he was scrolling through his phone and stared at her. “Thoughts?”
“And prayers,” he sassed. “Because you’re going to need them. Why the would you pick Gotham when Harvard accepted you?”
“Gotham has Arkham. And Doctor Quinzel.”
“Isn’t she Harley Quinn? The Crime Princess of Gotham?”
“Yeah, and an acclaimed psychologist with hundreds of published work that revolutionized the mental health field! Sure, she’s more criminally inclined now, but I’d kill to pick her brains.”
Danny grinned. “Interesting word choice. You’d fit right in. It’s just weird that all of their psychologists turned into villains.”
“Okay, but I won’t. You’d stop me.”
“Or I’d join you,” Danny rolled back onto the floor.
“Don’t you dare, Daniel Fenton. You’d better stop me if I went villain.”
“But I feel like you’d have a pretty good reason for it though?”
“I appreciate the trust, dumbass, but I’m always this close to loosing it.” Jazz rolled her eyes as she jabbed a finger at Danny.
“Hah! You’ll fit right into Gotham!”
Jazz hummed. “So, Gotham?”
“Yeah, why not?”
——
“Danny!”
“Little busy!” Danny dodged a blast from a GIW agent.
“Why’d you pick up, then?”
“You don’t call often- hey, can you guys knock it off? I’m on a call!” Danny shouted. Surprisingly the agents stopped.
“Woah. You guys actually stopped?”
“We’re anti-ghost, not rude cavemen. Finish your call, Phantom, so we can get back to capturing you.” The agent with red hair said. Her partner nodded their head.
“Riiiight.” Phantom floated away a bit. “What did you want to talk about?” He asked Jazz.
“So, Dr. Quinzel-”
Danny heard a further off “Call me Harley, darling!”
“Harley,” Jazz continued seamlessly. “Is dating Ivy, a meta! Which, totally cute and their relationship is so healthy. Goals, honestly-”
Danny heard another far off comment, “Awe, thanks, Jazzy-wazzy!”
“But long story short, they got in touch with the Justice League about the GIW and they’re getting pulled back! And disbanded! Are you fighting the agents? Can you see if they’ve got the order to pull back?”
“Wait, seriously?” Danny perked up, the exhaustion from the fight all but gone. “I’ll ask.”
Danny turned to the two agents, pulling the phone away from his ear. “Hey! Did you guys get orders to stop hunting me? I heard the Justice League got involved.”
“What? We didn’t-”
“Shit, wait, we got orders.” Her partner jabbed their phone at her.
“Fuck. This isn’t over, Phantom!”
“Yeah, yeah! Shoo!” Danny watched them peel away. “Thanks, Jazz! Maybe I’ll finally get a peaceful school year.”
“R.I.P.” Jazz solemnly intoned.
“Dead-ass.” Danny replied, just as seriously before the both of them broke. Cackling, Danny said goodbye to Jazz.
“Maybe I should get some gifts? Hm… Undergrowth has some rare plants.” Danny muttered as he flew back home.
2K notes · View notes
visenyaism · 3 months
Text
i also think that with the show’s whole poison colonialism symbolism goodsir’s thing where he turns to Silna and is like i wish you could come to england and see that there’s good people there we’re not like we are here goes crazy. like Dr. Goodsir you brought the empire with you!!! you all ARE the good people in england you are referring to. the land that you think turns you into monsters is her home and the monstrousness is fundamentally your own
1K notes · View notes
dailybloopy · 1 month
Text
Tumblr media
716 notes · View notes
carsonsweebabyturtles · 7 months
Text
Tumblr media
Dr. Beckett, Your Bad Practice/Dodgy Ethics Is Showing!!!!  (4/?) -
Weir: So what do you recommend?
Carson: That we take their work to the next level. I've informed the Hoffans of our guest in the brig.
Weir: You realise what you're asking for?
Carson: I do.
Poor Steve. Ok, yeah, he's a Wraith and they suck the life out of people. Carson is knowingly proposing sending this living, sentient being to his probable death but Steve is also a prisoner of war. That's more than just a little bit war crimey.
1 2 3
37 notes · View notes
twotales · 6 months
Text
we deserved more rodney & carson interactions
19 notes · View notes
Text
Tumblr media
Stargate-Atlantis S1: E6 Poisoning the Well
"A TV character Dr. Beckett plays in real life."
🤣🤣🤣 Beckett is so McCoy!
This is our first real Beckett episode. I think it may be the first time he calls someone "love." I love it when he says love or dear. I love Beckett so much, and I'm glad he got to play such a large role on the show.
I also love how Sheppard responds to the Wraith with such snark. It's hysterical. The Wraith are always intensely threatening and John is just calmly cocky to the point of annoyance.
This marks the first ethical dilemma for Atlantis when it comes to the Wraith. John is all for it. Elizabeth is hesitant. But when Steve actually dies because of the experiment, John is filled with pity.
(And let's not talk about the elephant in the room: even if almost a whole population agrees to try an untested vaccine, it doesn't make it right. Untested vaccines have unforseen side effects. We forgot the lessons of this episode real fast.)
4 notes · View notes
markscherz · 8 months
Note
Which frog is well-dressed but well-armed as well?
Personally I have huge respect for someone who commits to a suit that is all one colour, and centrolenid frogs (glass frogs) commit pretty hard to that style, though with occasional polka-dots for good measure. But don't let their high fashion fool you. They are very well armed—at least for battles with each other. Many glass frogs possess fearsome humeral spines; sharp extensions of the upper arm.
Tumblr media
[src]
Tumblr media
[src]
So they're pretty literally well-armed.
2K notes · View notes
gal-o-guacamole · 2 months
Text
Tumblr media
●Radiant is Gabriel●
Tumblr media Tumblr media Tumblr media
Feb.2024 (stained and artistic glass, copper, lead, gold and silver paint)
Process pics + vid ↷
Tumblr media Tumblr media Tumblr media Tumblr media Tumblr media Tumblr media
1K notes · View notes
Text
Tumblr media
obsessed with the prospect of Howdy Figuring It Out via the neighbors enjoying non-food items
1K notes · View notes