arXiv:2603. 21194v2 Announce Type: replace-cross Abstract: Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities.
arXiv:2607. 06807v1 Announce Type: cross Abstract: While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels.
arXiv:2608. 01085v1 Announce Type: cross Abstract: LLM-based multi-agent systems (MAS) extend LLM capabilities through iterative communication and shared contexts.
arXiv:2607. 07368v1 Announce Type: cross Abstract: AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent.
arXiv:2606. 12737v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources.
MAS-Shield is a defense framework for Large Language Model–based Multi-Agent Systems that uses a coarse‑to‑fine filtering pipeline. It first selects critical agents, then applies lightweight auditing to most cases, and finally escalates only suspicious signals to a heavyweight committee. Experiments show a 92.5% recovery rate against adversarial attacks and a latency reduction of over 70% compared to existing methods.
MiniRep is a reputation‑based aggregation system designed for multi‑agent debate (MAD) that remains robust even when malicious agents are present. It evaluates agents on both their current task performance and historical reputation, while preventing groups of agents with highly similar responses from dominating the final decision. Experiments on the MATH benchmark show that MiniRep consistently outperforms conventional MAD aggregation and other reputation‑based approaches across a wide range of attack scenarios.
arXiv:2505. 23847v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise without surrendering data ownership.
The paper introduces the Generic Multi-Agent Trading System (GMATS), a framework for studying how large language model (LLM) based trading stacks react to black-box, input-only attacks that inject plausible social‑media content. It defines contagion metrics—belief‑shift scores at analyst and coordinator layers and attack‑clean deltas on backtest metrics—to trace the spread of adversarial signals. Experiments on a safe offline benchmark show that even simple attackers can significantly degrade risk‑return profiles, while certain multi‑agent topologies and coordinator prompts can mitigate these effects.
arXiv:2605. 01133v3 Announce Type: replace-cross Abstract: Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks.
arXiv:2606. 30602v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows.
arXiv:2606.17092v2 Announce Type: replace-cross Abstract: Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex convers...
The paper investigates how adversarial signals can infiltrate large‑language‑model (LLM) based multi‑agent trading systems through the agents’ communication channels. By restricting the attacker to realistic inputs—source data and prompts—it studies role‑specific attacks on four functional roles (Analyst, Researcher, Trader, Risk Manager) and evaluates four communication topologies under data‑ and agent‑level attacks. Experiments across multiple assets, backbones, and target directions show that no architecture is inherently robust, highlighting the need for safer designs in agentic trading systems.