视觉生成式人工智能模型(如 DALL-E 3、Stable Diffusion XL、Stable Video Diffusion 和 Sora)的受欢迎程度持续上升。通过广泛评估,我们发现最先进的视觉生成模型能够生成与主要娱乐公司(如 Sony、Marvel 和 Nintendo)所持有的受知识产权保护的角色高度相似的内容,这可能引发潜在的法律问题。当输入提示包含角色名称,甚至仅包含其外观特征的描述性细节时,这种情况就会发生。为了缓解此类知识产权侵权问题,我们还提出了一种防御方法。具体而言,我们开发了一种改进的生成范式,该范式能够识别可能侵权的生成内容,并通过在扩散过程中利用引导技术来防止知识产权侵权。该方法具备识别可能侵犯知识产权的生成内容的能力,并在整个扩散过程中采用引导方法来缓解此类侵权,而无需重新训练或微调预训练模型。在 Spider-Man、Iron Man 和 Superman 等知名角色知识产权上的实验证明了所提防御方法的有效性。我们的数据和代码可在 https://github.com/ZhentingWang/GAI_IP_Infringement 获取。
英文摘要:
The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered that the state-of-the-art visual generative models can generate content that bears a striking resemblance to characters protected by intellectual property rights held by major entertainment companies (such as Sony, Marvel, and Nintendo), which raises potential legal concerns. This happens when the input prompt contains the character's name or even just descriptive details about their characteristics. To mitigate such IP infringement problems, we also propose a defense method against it. In detail, we develop a revised generation paradigm that can identify potentially infringing generated content and prevent IP infringement by utilizing guidance techniques during the diffusion process. It has the capability to recognize generated content that may be infringing on intellectual property rights, and mitigate such infringement by employing guidance methods throughout the diffusion process without retrain or fine-tune the pretrained models. Experiments on well-known character IPs like Spider-Man, Iron Man, and Superman demonstrate the effectiveness of the proposed defense method. Our data and code can be found at https://github.com/ZhentingWang/GAI_IP_Infringement.
AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Models
Florida International University, Miami, Florida, United States(佛罗里达国际大学);Guangdong University of Foreign Studies, Guangzhou, Guangdong, China(广东外语外贸大学);Carnegie Mellon University, Pittsburgh, Pennsylvania, United States(卡内基梅隆大学)
Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized
RWTH Aachen University(亚琛工业大学);National University of Singapore(新加坡国立大学);Fraunhofer Institute for Applied Information Technology FIT(弗劳恩霍夫应用信息技术研究所FIT)
MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue
College of Intelligent Robotics and Advanced Manufacturing, Fudan University(复旦大学智能机器人与先进制造学院);Southern University of Science and Technology(南方科技大学);TMLR Group, Hong Kong Baptist University(香港 Baptist 大学 TMLR 团体);MM Lab, CUHK(CUHK 多模态实验室);RAMS Lab, Huawei Technologies Co., Ltd.(华为技术有限公司 RAMS 实验室)
VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models
College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University(吉林大学计算机科学与技术学院,符号计算与知识工程重点实验室,教育部,吉林大学);College of Software, Jilin University(吉林大学软件学院);Facemind Group(FaceMind集团);School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机科学与信息工程学院)
Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion
School of Computer Science, Tel Aviv University(特拉维夫大学计算机科学学院);Faculty of Law, Tel Aviv University(特拉维夫大学法学院);School of Electrical Engineering, Tel Aviv University(特拉维夫大学电气工程学院)