6 mentions in 7 days · 6 in 30 days · 6 total · first seen · last
A multi-agent system vulnerability is identified where remote names are used as routing identifiers, causing wrong-peer dispatch.
This research paper describes an Agent Name Collision Attack in Multi-Agent Systems, where remote names are used as routing identifiers, causing wrong-peer dispatch.
A paper introduces a standardized CACAO integration registry with quality-gating for cybersecurity integration management.
This paper introduces a Common CACAO Registry for standardized cybersecurity integration and provides a quality-gated approach to integration management.
This paper demonstrates that controlling token injection can suppress chain-of-thought in tool-using agents.
This paper shows that appending channel-control tokens can suppress chain-of-thought in tool-using agents, reducing their reasoning and tool execution.
This paper presents a state-recovery defense for traffic signal control under sensor corruption.
This paper presents a state-recovery defense for traffic signal control against sensor corruption and adversarial attacks.
This paper describes a method to keep issuing bank control over agent payments.
This paper describes a method to keep the issuing bank control over agent payments by enforcing spending rules and validating payments.
A study of public-sector AI registers and inventories finds missing data and proposes a layered visibility framework for transparency and interoperability.
This paper compares 8,368 public-sector AI records across 72 countries and finds broad schemas have substantial missingness, with limitations in transparency and interoperability, proposing a layered visibility framework.