Here is the result after two evenings!
#sciart #watercolors #fungifriends #fungi #badvideo

It works, I'm at full panic. #panic #button #daily #badvideo #sapspeaks

That said, haven't seen much research about poisoning video models yet. Did anything Nightshade-like come out for video?
I'm aware of BadVideo injecting new information into video models' output, and a number of jailbreak papers, but a cursory search doesn't turn up anything.

Anybody here roller skate? Drop your handle, let's spin into a new social world together #quadskater #rollergirl #badvideo #itwasaniphone10 #artist #flow

Misinformation about Undertale 5 minutes in #badvideo

Pov:當你被嚇到時你好友在你旁邊：
#originalcharacter #gachaclub #vine #原創角色#ocsona #oc #alightmotion #badvideo #fyp #idk
(嗯對我有玩gacha但是不常用

anyone who has me on tiktok if you see my reposts getting absurd -- its very likely my friend is over trying to out-badvideo me

dimension of videos, our attack successfully evades traditional content moderation systems that primarily analyze spatial information within individual frames. Extensive experiments demonstrate that BadVideo achieves high attack success rates while [6/8 of https://arxiv.org/abs/2504.16907v1]

additional details, providing opportunities for malicious attackers to embed hidden harmful content. Exploiting this inherent redundancy, we introduce BadVideo, the first backdoor attack framework tailored for T2V generation. Our attack focuses on [3/8 of https://arxiv.org/abs/2504.16907v1]

Ruotong Wang, Mingli Zhu, Jiarong Ou, Rui Chen, Xin Tao, Pengfei Wan, Baoyuan Wu: BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation https://arxiv.org/abs/2504.16907 https://arxiv.org/pdf/2504.16907 https://arxiv.org/html/2504.16907

[2025-07-29] 📚 Updates in #DiffM

(1) BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation
(2) Generative Pre-training for Subjective Tasks: A Diffusion Transformer-Based Framework for Facial Beauty Prediction

🔍 More at researchtrend.ai/communities/DiffM

[2025-07-29] 📚 Updates in #AAML

(1) BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation
(2) Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks

🔍 More at researchtrend.ai/communities/AAML

[2025-07-29] 📚 Updates in #VGen

(1) BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation
(2) <a href="https://researchtrend.ai/papers/2501.06250" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">Generative AI for Cel-Animation: A Survey
(3) Generative AI for Cel-Animation: A Survey

🔍 More at researchtrend.ai/communities/VGen

Discover the brilliance behind Michael Jackson's iconic dance moves in the 'Bad' video! From mesmerising leans to unforgettable gangster imagery, today!#MichaelJackson #DanceMoves #BadVideo #KingOfPop #Entertainment

Ruotong Wang, Mingli Zhu, Jiarong Ou, Rui Chen, Xin Tao, Pengfei Wan, Baoyuan Wu
BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation
https://arxiv.org/abs/2504.16907