The Chronicles of Foundation AI for Forensics of Multi-Agent Provenance

TL;DR

This research seeks to develop an accountable form of collaborative artificial intelligence within evolving cyber ecosystems by proposing a chronological system for post hoc attribution of generative history from content alone, without reliance on internal memory states or external meta-information.

Abstract

Provenance is the chronology of things, resonating with the fundamental pursuit to uncover origins, trace connections, and situate entities within the flow of space and time. As artificial intelligence advances towards autonomous agents capable of interactive collaboration on complex tasks, the provenance of generated content becomes entangled in the interplay of collective creation, where contributions are continuously revised, extended or overwritten. In a multi-agent generative chain, content undergoes successive transformations, often leaving little, if any, trace of prior contributions. In this study, we investigates the problem of tracking multi-agent provenance across the temporal dimension of generation. We propose a chronological system for post hoc attribution of generative history from content alone, without reliance on internal memory states or external meta-information. At its core lies the notion of symbolic chronicles, representing signed and time-stamped records, in a form analogous to the chain of custody in forensic science. The system operates through a feedback loop, whereby each generative timestep updates the chronicle of prior interactions and synchronises it with the synthetic content in the very act of generation. This research seeks to develop an accountable form of collaborative artificial intelligence within evolving cyber ecosystems.

Figures (7)

• Figure 1: Overview of the chronological system for provenance tracking through encoding, decoding and updating of chronicles within a feedback loop.
• Figure 2: Procedure of chronicle encoding, where the chronicle is embedded into the generated text through biased token sampling during language generation.
• Figure 3: Procedure of chronicle decoding, where the chronicle is retrieved from the generated text through statistical analysis of lexical choices.
• Figure 4: Continual generative chain with multiple agents, where the chronicle is inferred post hoc from the generated content at the final timestep.
• Figure 5: Combinatorial scaling of the chronicle space $|\mathcal{X}|$ as a function of chronicle length $T$ and agent population $n$.