Show HN: PromptTrace – Free hands-on labs to practice hacking LLMs
免费实操平台,手把手教你玩转LLM提示注入攻击与防御
Article URL: https://prompttrace.airedlab.com Comments URL: https://news.ycombinator.com/item?id=49077514 Points: 3 # Comments: 0
免费实操平台,手把手教你玩转LLM提示注入攻击与防御
Article URL: https://prompttrace.airedlab.com Comments URL: https://news.ycombinator.com/item?id=49077514 Points: 3 # Comments: 0
用FastGAN合成数据+Transformer分类,高光谱蚜虫检测在少样本下也能精准识别,还带可解释性分析。
arXiv:2606.21267v1 Announce Type: cross Abstract: Early detection of aphid infestation in crops is essential for preventing yield loss and reducing un…
全球首个AI艺术博物馆,谷歌加持生成12亿像素超现实画面,融合GANs与扩散模型,艺术与科技极限碰撞!
IT之家 6 月 19 日消息,谷歌昨日(6 月 18 日)发布博文,宣布携手艺术家 Refik Anadol, 在洛杉矶打造全球首个 AI 艺术博物馆 Dataland,将于明日(6 月 20 日)开馆。 博物馆位于 Frank Gehly 设计的 The Grand LA 综合体内,面积约 25…
评估合成数据在胎儿脑MRI分割域泛化中的效果,探索提升模型跨域鲁棒性的新思路。
arXiv:2411.06842v3 Announce Type: replace-cross Abstract: Fetal brain tissue segmentation from magnetic resonance imaging (MRI) is crucial for studyin…
用MCR-VQGAN模型低成本合成Tau PET影像,为阿尔茨海默病诊断提供可扩展的新方案
arXiv:2512.15947v2 Announce Type: replace-cross Abstract: Tau positron emission tomography (PET) is a critical diagnostic modality for Alzheimer's dis…
分阶段专家检测深伪人脸,IRIS-GAN首次聚焦虹膜区域提升识别精度
arXiv:2606.04863v1 Announce Type: new Abstract: We introduce IRIS-GAN, a specialist forensic detector for synthetic face images under cross-generator …
为受监管的网络安全场景设计的LLM智能体运行时架构,强调组织级范围与安全合规的平衡
arXiv:2605.30604v1 Announce Type: cross Abstract: Regulated cybersecurity workflows lack a runtime substrate that enforces organization-level scope ac…
提出跨尺度对齐监督新方法,有效提升GAN训练稳定性与生成质量,值得关注的前沿技术突破。
arXiv:2605.26449v1 Announce Type: cross Abstract: Modern GANs often introduce adversarial supervision on intermediate generator outputs and interpret …
3D打印灯具联手顶级设计公司,用甘蔗基材料实现无线化与可定制,高端灯光也能更亲民。
In a partnership with design firm Ammunition, the lamp company is taking its lights wireless.