← 研踪 PaperTrailarXiv:2611.21455 · v1
Synthetic Doubt and the Integrity of Digital Proof before the International Criminal Court
首次提交 2026-11-17 01:41
版本更新 2026-11-17 01:41
雷达观测 2026-11-17 16:10
摘要
Generative artificial intelligence complicates evidentiary assessment at the International Criminal Court by enabling fabricated audiovisual material and making authentic digital evidence easier to dismiss as fake. This article calls the latter problem synthetic doubt: an objection alleging that a digital item may be AI-generated or AI-manipulated. Existing scholarship addresses digital evidence, open-source investigations and deepfakes in the ICC context. Yet the question of when synthetic doubt should trigger enhanced reliability review under the Rome Statute, without displacing the prosecution's burden under article 66 or compromising article 67 fair-trial rights, remains underdeveloped. The article proposes a three-stage framework: a baseline authenticity and provenance showing by the proponent; a case-specific articulation threshold for the objector; and proportionate reliability review by the Chamber under articles 64 and 69(4). The framework treats AI-related provenance information and synthetic-media detector outputs as contextual rather than dispositive.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 01:41 · 最新观测版本
Synthetic Doubt and the Integrity of Digital Proof before the International Criminal Court
Generative artificial intelligence complicates evidentiary assessment at the International Criminal Court by enabling fabricated audiovisual material and making authentic digital evidence easier to dismiss as fake. This article calls the latter problem synthetic doubt: an objection alleging that a digital item may be AI-generated or AI-manipulated. Existing scholarship addresses digital evidence, open-source investigations and deepfakes in the ICC context. Yet the question of when synthetic doubt should trigger enhanced reliability review under the Rome Statute, without displacing the prosecution's burden under article 66 or compromising article 67 fair-trial rights, remains underdeveloped. The article proposes a three-stage framework: a baseline authenticity and provenance showing by the proponent; a case-specific articulation threshold for the objector; and proportionate reliability review by the Chamber under articles 64 and 69(4). The framework treats AI-related provenance information and synthetic-media detector outputs as contextual rather than dispositive.
查看此版本解读 →查看此版本原文 ↗