Aug 2026· 1 citation· ⚡ 1 influential· 23 references
Computer Science
TL;DR
The selection-invariant communication compiler (SICC), which constrains this post-authorization representation kernel rather than prescribing templates, is introduced, which proves a compositional communication-layer guarantee.
Abstract
Structured multi-agent workflows exchange intermediate messages whose content and form can reveal private state even when the final output is safe. We identify selection-channel leakage: after authorization fixes what may be released, a private-state-aware choice among semantically valid realizations creates an additional inference channel. We introduce the selection-invariant communication compiler(SICC), which constrains this post-authorization representation kernel rather than prescribing templates. Any deterministic or independently public-randomized generator satisfying the invariant is valid; requirement-indexed canonical forms are one auditable implementation. We prove a compositional communication-layer guarantee: authorization, public-only form generation, and a dependency-safe utility gate make the emitted transcript reveal no information beyond the complete authorized view. Private-state-aware selection remains vulnerable after surface-disjoint and length-matched controls. Across 132 AgentLeak communication replays and 100 executable LangGraph tasks, deterministic SICC retains complete protocol utility without a positive excess-gain signal; independent public randomization preserves the same result in AgentLeak and 480 controlled cases.
LLM-agent workflows routinely transform rich observations into plans, summaries, memories, handoffs, and other reusable state. This creates a privacy boundary that task relevance alone does not capture: an observation may be needed as evidence for a task without its full semantics being authorized to persist. We call t...
Dong-Sheng Chen, Xiang-Yu Zhao, Lei Ma et al.· 0 citations
The results show that plan-first execution combined with label-preserving persistence can substantially strengthen persistent LLM agents, while revealing an important security-utility tradeoff introduced by strict integrity enforcement.
KITA is presented, a review-to-authorization architecture that keeps the user's personal secret signing key and every threshold signing-key share outside all LLM processes and establishes execution-bound authorization integrity.
VeriCrypt-Agent is presented, an evidence-grounded workflow for bounded-autonomy cryptographic maintenance that combines a frozen snapshot of release/advisory evidence, a public catalog of project-level executable probes, cross-version execution under old and candidate dependency versions, role-specialized LLM reasonin...
V. Tynchenko, Alexey S. Borodulin, Dmitriy Martysyuk et al.· Computers· 0 citations
MutMem V2 supports claims about portable integrity, authorization, traceability, conformance, and reproducibility under stated assumptions; it does not establish semantic truth, universal robustness, or independent replication.
This work presents PAPC, a platform-mediated mechanism that intercepts information-moving events before they update shared state or external channels and positions event-level mediation as a platform-governance primitive for agent-mediated online work.
Tao Huang, Guo-Xin Wu, Chen Hou et al.· 0 citations