基炽🐣🍴
@jichichickenwing.bsky.social
=jichi=ツバサキ
絵：雑多✍️日本語：下手💦語彙力：残念🙇♀️
️⚠️转载、AI学習禁止
絵：雑多✍️日本語：下手💦語彙力：残念🙇♀️
️⚠️转载、AI学習禁止
Pinned
Reposted by 基炽🐣🍴
Update thread #2. Hemlock
One thing we worked on is a different tool to complement Nightshade. We discovered a new attack on diffusion models that is more generalizable than Nightshade. It targets an entirely different part of AI training pipeline, basically making AI models poison themselves.
One thing we worked on is a different tool to complement Nightshade. We discovered a new attack on diffusion models that is more generalizable than Nightshade. It targets an entirely different part of AI training pipeline, basically making AI models poison themselves.
July 12, 2025 at 5:36 AM
Update thread #2. Hemlock
One thing we worked on is a different tool to complement Nightshade. We discovered a new attack on diffusion models that is more generalizable than Nightshade. It targets an entirely different part of AI training pipeline, basically making AI models poison themselves.
One thing we worked on is a different tool to complement Nightshade. We discovered a new attack on diffusion models that is more generalizable than Nightshade. It targets an entirely different part of AI training pipeline, basically making AI models poison themselves.
