arXiv:2607. 08400v1 Announce Type: cross Abstract: LLM agents reach users through resellers, who may rebrand a developer's agent or substitute a cheaper model.
The paper introduces an adaptive embedding displacement attack (EDA) that exploits rewording, reordering, and resegmentation to remove semantic watermarks from text, achieving a 32.6%–47.9% success rate across four watermarking schemes. To counter this, the authors propose k‑SwordStamp, a semantic watermarking method that uses order‑robust detection over sub‑sentence units, significantly reducing vulnerability to structure‑based edits. Experiments show that EDA remains effective against k‑SwordStamp, but with a lower success rate (10.8%) compared to its performance on other schemes.
arXiv:2609.37310v1 Announce Type: cross Abstract: With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Ye...
arXiv:2606. 07316v1 Announce Type: cross Abstract: Byzantine collaboration among large-language-model agents requires a finality-control primitive: given delivered stochastic, structured natural-language proposals, the protocol must decide whether the round supports a commit, what kind of commit, or a typed safe abort.
arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.
BodhiPromptShield is a policy‑aware mediation layer for LLM agent pipelines that detects sensitive text spans before they propagate, replacing them with typed placeholders, semantic abstractions, or secure tokens and restoring them only at authorized execution boundaries. In evaluations on AI4Privacy, PrivacyLens, and AgentDojo datasets, the system reduces identifier exposure to 7.4% and 1.8% respectively, and limits exact identifier leakage in final actions to 2.1–3.1%. While mediation preserves factual content according to automated metrics, human annotations show a significant drop in inferability from 100% to 24–53%, indicating the need for human validation of semantic‑leakage measures.
arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.
MoSign is a challenge-response authentication system that embeds a time‑varying keyed message into the motion of virtual‑reality users, allowing them to prove identity while keeping their avatars anonymous. The watermark is added to the latent space of a motion variational autoencoder and is provably indistinguishable from unwatermarked motion, with security tied to breaking a pseudorandom function. Experiments on HumanML3D and BOXRR‑23 show high authentication accuracy, low false‑accept rates, and resilience against realistic recapture attacks while remaining undetectable by standard detectors.
The paper introduces a claim‑anchored execution contract that binds a tool‑using agent’s emitted claim to its exact source span, the ordered execution prefix that produced it, and the source version and access state observed. Each receipt contains deterministic anchors, source identifiers, offsets, hashes, quotes, and a domain‑separated execution commitment, allowing a verifier to reconstruct these bindings before semantic or task labels are joined. The contract defines seven independently testable properties and demonstrates high detection rates against cross‑object attacks, with strong performance on conflict‑aware support guard evaluations.
arXiv:2607. 13003v1 Announce Type: cross Abstract: A watermark in a generative model's output is usually asked only whether a text is machine-made.
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
arXiv:2606. 08539v1 Announce Type: new Abstract: AI agents increasingly take consequential actions -- shell commands, cloud operations, and arbitrary tool-calls -- so a trust layer must decide, per action, whether to allow, warn, block, or escalate.