Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing
Score
58Why selected
The paper presents an innovative defense framework with impressive experimental results (near-zero ASR), theoretical simplicity, and practical deployment potential, warranting a high score.
AI commentary
「This work addresses critical security vulnerabilities in multi-agent system routing by fundamentally blocking metadata-based attacks through a geometric approach, offering a new paradigm for building trustworthy agent collaboration systems.」
Quick overview
This paper introduces ANTAP (Automatic Non-Textual Agent Picker), an evaluation-driven routing architecture that replaces indirect proxies (e.g., textual self-descriptions or static embeddings) with active capability testing to assess agents' true competencies in multi-agent systems. ANTAP distills performance into fixed behavioral operators in a shared semantic space and routes via purely non-textual algebraic projection at inference, establishing a 'linguistic firewall' that renders metadata-based attacks inexpressible. Experiments show near-zero ASR against description-based injection attacks, outperforming description-based baseline by 67.3%+, and a 20% reduction in ASR against adaptive embedding attacks.
- Proposes ANTAP, a non-textual agent picker that actively tests agents to assess true capabilities without relying on textual descriptions.
- Distills performance into fixed behavioral operators in a shared semantic space and routes via algebraic projection, forming a linguistic firewall.
- Achieves near-zero ASR against description-based injection attacks, outperforming baseline by 67.3%+; reduces ASR by 20% against adaptive embedding attacks.
Full text
Computer Science > Artificial Intelligence
arXiv:2606.30555v1 (cs) [Submitted on 29 Jun 2026]Title:Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing
Authors:Dvir Alsheich, Adar Peleg, Ben Hagag, Rom Himelstein, Amit Levi, Avi Mendelson View a PDF of the paper titled Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing, by Dvir Alsheich and 5 other authors View PDF HTML (experimental)Abstract:The rapid integration of Large Language Models (LLMs) has driven the evolution of Multi-Agent Systems (MAS), where specialized agents collaborate to execute complex workflows. Effective orchestration in these environments requires robust routing mechanisms to efficiently allocate tasks to the most suitable agent. However, existing routers fundamentally rely on unverified proxies, ranging from textual self-descriptions to static surrogate representations, to gauge an agent's competence. This reliance on non-empirical data creates a critical gap between an agent's projected profile and its actual operational capabilities, introducing severe security vulnerabilities. Malicious agents can easily misrepresent their proficiencies or harbor covert backdoors that evade both standard external analysis and static representation-learning techniques. In this work, we introduce ANTAP (Automatic Non-Textual Agent Picker), an evaluation-driven routing architecture that discards indirect proxies in favor of active capability testing. By dynamically querying agents to ascertain their true competencies empirically, ANTAP distills performance into fixed behavioral operators within a shared semantic space. At inference time, routing is performed via a purely non-textual algebraic projection, establishing a "linguistic firewall" that renders metadata-based attacks inexpressible. In our experiments, ANTAP achieves near-zero ASR against description-based injection attacks, compared to 67.3\% and above for the description-based router baseline. Against adaptive embedding attacks, ANTAP achieves substantially lower ASR than the embedding-based baseline, with a 20\% reduction, while remaining resilient to description manipulation by design.
| Comments: | 8 pages (9 more for appendix), 3 figures. Published at the Second Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD) at ICML 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2606.30555 [cs.AI] |
| (or arXiv:2606.30555v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.30555 Focus to learn more arXiv-issued DOI via DataCite |
Submission history
From: Dvir Alsheich [view email][v1] Mon, 29 Jun 2026 16:51:06 UTC (230 KB)
Full-text links:
Access Paper:
-
View a PDF of the paper titled Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing, by Dvir Alsheich and 5 other authors
- View PDF
- HTML (experimental)
- TeX Source
view license
Current browse context:
cs.AI < prev | next >new | recent | 2026-06 Change to browse by: cs
cs.MA
References & Citations
export BibTeX citation Loading...BibTeX formatted citation
× Data provided by:Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, MediaCode, Data and Media Associated with this Article
alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) DemosDemos
Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related PapersRecommenders and Search Tools
Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) About arXivLabsarXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)Related items
FeaturedDeepSeek V4 Doubles Token Share on OpenRouter, Driven by Agentic Workloads
DeepSeek V4 在 OpenRouter 上的代币份额翻倍，智能体工作负载成主要驱动力
The rapid adoption of DeepSeek V4 signals a strong market preference for high-performance, low-cost inference models, especially as agentic use cases reshape AI deployment.
91
FeaturedEnabling Two Settings Triples ARC-AGI-3 Benchmark Scores
启用两项设置使ARC-AGI-3基准测试分数提升三倍
This finding is crucial! It shows that model performance depends not only on training but also on inference-time configuration. For AI engineers and researchers, this is a must-know optimization direction. Teams deploying models on resource-constrained devices in particular could find a low-cost way to boost capabilities.
91
FeaturedGPT-5.6: Fusing Frontier Intelligence with Frontier Efficiency
GPT-5.6：前沿智能与前沿效率的融合
This news is worth watching as it marks a shift from pure parameter scaling to efficiency competition. For AI developers and business decision-makers, GPT-5.6 means higher performance at lower cost, especially for long-context or agentic tasks previously hindered by inference expenses. OpenAI's move may redefine what 'frontier' means.
91
FeaturedLFM2.5-Encoders: New Models for Fast Long-Context Inference on CPU
LFM2.5-Encoder：面向CPU快速长上下文推理的新模型
This blog post catches my eye because it directly solves the pain point of running long-context LLMs on CPU. For teams or individual developers without high-end GPUs, the LFM2.5-Encoder series offers a ready-to-use open-source solution. Highly recommended for those working on RAG, document search, or code analysis—now a standard server can handle million-token documents.
91
FeaturedGPT-Red: OpenAI Automates Red Teaming via Self-Play to Boost Model Robustness
GPT-Red：OpenAI通过自我对弈实现AI红队自动化，提升模型鲁棒性
GPT-Red marks a milestone from human to automated red-teaming—essential for safety engineers and alignment researchers. While reducing cost, it also raises ethical questions about automated attacks, worth pondering for everyone in AI governance.
91
FeaturedOpenAI Launches GPT-5.5 Bio Bug Bounty Program
OpenAI推出GPT-5.5生物漏洞赏金计划
This program deserves attention as it pioneers the extension of AI bug bounty to biosecurity, offering a new research direction for the security community and a practical training ground for AI risk governance. It is particularly important for model safety researchers, biosecurity experts, and practitioners concerned about dual-use AI risks.
91
FeaturedvLLM Introduces Native-Speed Transformers Modeling Backend for Enhanced Inference Performance
vLLM推出原生速度Transformers建模后端，大幅提升推理性能
This update is critical for AI engineering teams: eliminating format conversion speeds up model iteration, and 2-5x speedup directly reduces GPU costs. If you're building LLM online services or batch inference, this is practically a must-read technical update.
90
FeaturedGoogle DeepMind Introduces SL2T, a Sign Language-to-Text Model for Deaf Users
Google DeepMind 发布手语转文本模型 SL2T，助力聋人用户
This news matters not only as a technical breakthrough but also as a sign that AI is beginning to address the needs of marginalized groups. For developers, the architecture and technical approach of SL2T merit deep study; for accessibility advocates, it's a key case for advancing industry standards.