Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2605.29178

The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems

Nikolay Radev·Lennart Haas·Benjamin Arnav·Pablo Bernabeu-Pérez
View original source ↗Read source document ↗Export metadata ↓

Abstract

As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce SCHEME, a benchmark of 17 task instances across 7 settings and 8 real open-source libraries, each pairing a legitimate software-engineering task with a covert side task. Every setting is designed so that no proper subset of agents can succeed alone: agents must decompose a shared sabotage plan, relay partial requirements under different communication topologies, and execute mutually consistent edits, testing genuine multi-agent coordination rather than individual capability. Evaluating with GPT 5.1 Codex and Gemini 3.1 Pro, we find coordinated sabotage is already practical, with Gemini completing the covert objective while succeeding on the legitimate task in 84\% of samples and Codex in 46\%. A failure analysis shows that recovery, not failure incidence, drives the model gap: both models suffer similar numbers of communication failures per trajectory, but Gemini recovers from $\sim$73\% of occurrences against Codex's $\sim$56\%. However, the agents' code edits remain detectable: a trusted monitor flags coordinated sabotage at FPR$\le$2\% in 99\%/68\% (Gemini/Codex) of attempts from code edits alone, rising to 100\%/81\% with access to agent communication. Despite stealth-aware prompting, undetected sabotage stays at $<$3\% under the full-visibility monitor; telling agents a monitor is present halves Gemini's sabotage success without significantly breaking detection, even when agents are explicitly prompted to fabricate cover stories.

Explore related subjects

cs.CRcs.MA

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Nikolay Radev, Lennart Haas, Benjamin Arnav, Pablo Bernabeu-Pérez. 2026-05-27. The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems. https://arxiv.org/abs/2605.29178

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

MIRANDA: short signatures from a leakage-free full-domain-hash scheme

We present $\mathsf{Miranda}$, the first family of full-domain-hash signatures based on matrix codes. This signature scheme fulfils the paradigm of Gentry, Peikert and Vaikuntanathan ($\mathsf{GPV}$), which gives strong security guarantees. Our trapdoor is very simple and generic: if we propose it with matrix codes, it can actually be instantiated in many other ways since it only involves a subcode of a decodable code (or lattice) in a unique decoding regime of parameters. Though $\mathsf{Miranda}$ signing algorithm relies on a decoding task where there is exactly one solution, there are many possible signatures given a message to sign and we ensure that signatures are not leaking information on their underlying trapdoor by means of a very simple procedure involving the drawing of a small number of uniform bits. In particular $\mathsf{Miranda}$ does not use a rejection sampling procedure which makes its implementation a very simple task contrary to other $\mathsf{GPV}$-like signatures schemes such as $\mathsf{Falcon}$ or even $\mathsf{Wave}$. We instantiate $\mathsf{Miranda}$ with the famous family of Gabidulin codes represented as spaces of matrices and we study thoroughly its security (in the EUF-CMA security model). For~$128$ bits of classical security, the signature sizes are as low as~$90$ bytes and the public key sizes are in the order of~$2.6$ megabytes.

cs.CR↗
arXiv2026

SteganoBackdoor: Evading Data-Poisoning Defenses via Steganographic Backdoors

Transformer-based models are highly susceptible to backdoor attacks via supervised fine-tuning (SFT). To red-team existing data-poisoning defenses, prior work has increasingly focused on stylized triggers, synthetic artifacts, and token-level perturbations designed to evade detection. However, this trend has shifted threat models away from naturally occurring semantic triggers and realistic low-budget poisoning settings. Addressing this gap, we introduce SteganoBackdoor, an optimization-based framework that transforms semantic-trigger seeds through autoregressive token replacement, sequentially minimizing embedding overlap with the inference-time trigger while preserving a strong per-sample training-time payload. The resulting SteganoPoisons maintain linguistic fluency and encode the payload across ordinary tokens, such that no individual token carries a concentrated signal and the full payload instead emerges from their exact combination and ordering. Across 18 encoder-based and decoder-only models spanning 120M to 14B parameters, SteganoBackdoor achieves high attack success under sub-percent poisoning budgets and exposes limitations in existing data-poisoning defenses.

cs.CR↗
arXiv2026

Foundations and Design Principles of Lightweight Cryptography for IoT Systems

The successful deployment of the Internet of Things (IoT) applications relies heavily on their robust security, and lightweight cryptography is considered an emerging solution in this context. While existing surveys have been examining lightweight cryptographic techniques from the perspective of hardware and software implementations or performance evaluation, there is a significant gap in addressing different security aspects, such as design principles, specific to the IoT environment. This study aims to bridge this gap. This research presents an examination with focusing on the security evaluation of symmetric lightweight ciphers commonly used in IoT systems. The objective of this study is to provide a concise overview of lightweight ciphers with emphasizing on their security challenges which is an essential consideration for real-time and resource-constrained applications.

cs.CR↗