PulseAugur
实时 16:04:42
实体 Ching-Chun Chang

Ching-Chun Chang

PulseAugur coverage of Ching-Chun Chang — every cluster mentioning Ching-Chun Chang across labs, papers, and developer communities, ranked by signal.

Show in brief
总计 · 30天
4
90 天内 4
发布 · 30天
0
90 天内 0
论文 · 30天
4
90 天内 4
层级分布 · 90 天
最近 · 第 1/1 页 · 共 4 条
  1. RESEARCH · CL_11780 ·

    AI forensics paper introduces watermarks for synthetic media transformation analysis

    Researchers have developed a novel watermarking system designed to trace the generation process of synthetic media, addressing the challenges posed by AI-driven image manipulation. This system creates 'tell-tale' waterm…

  2. RESEARCH · CL_11766 ·

    Researchers develop machine unlearning to counter AI backdoor threats

    Researchers have developed a novel machine unlearning framework to combat neural backdoors, which are cybersecurity vulnerabilities that can be exploited to manipulate AI systems. The proposed method uses psychometrics …

  3. RESEARCH · CL_11751 ·

    AI research proposes chronological system for multi-agent provenance tracking

    Researchers have developed a novel system to track the provenance of information generated by multiple AI agents. This system creates symbolic chronicles, akin to a chain of custody, to record signed and time-stamped co…

  4. RESEARCH · CL_11750 ·

    新的AI防御框架使用模仿博弈来对抗对抗性幻觉

    研究人员开发了一种新的防御机制,用于对抗生成式AI模型的对抗性攻击,称为“用于对抗性幻觉的模仿博弈”。该方法利用一个由链式思考推理引导的多模态生成代理来理解和重建数据的核心含义,而不是试图逆转它。实验证明了该框架在各种攻击场景中有效消除演绎性和归纳性对抗性幻觉的能力。