adversaries

Mentions · 7d0
Mentions · 30d0
All mentions5
First seenSep 23, 2026
Last mentionedSep 23, 2026

Timeline

5 articles · newest first

Agent Name Collision Attacks in Multi-Agent Systems

A multi-agent system vulnerability is identified where remote names are used as routing identifiers, causing wrong-peer dispatch.

arXiv cs.CRSep 23, 09:46 UTC · Sep 23, 2026Research2 · 2 reads

CCR: Towards a Common, Quality-Gated CACAO Integrations Registry for European Cybersecurity Automation

A paper introduces a standardized CACAO integration registry with quality-gating for cybersecurity integration management.

arXiv cs.CRSep 23, 08:49 UTC · Sep 23, 2026Research1

Control-Token Injection Suppresses Chain-of-Thought and Defeats Reasoning-Based Oversight in Tool-Using Agents

This paper demonstrates that controlling token injection can suppress chain-of-thought in tool-using agents.

arXiv cs.CRSep 23, 08:33 UTC · Sep 23, 2026AI research1 · 1 read

MDRC: A Deployable State-Recovery Defense for Traffic Signal Control under Sensor Corruption

This paper presents a state-recovery defense for traffic signal control under sensor corruption.

arXiv cs.CRSep 23, 08:22 UTC · Sep 23, 2026Research2 · 2 reads

Issuer-Sovereign Agentic Payments

This paper describes a method to keep issuing bank control over agent payments.

arXiv cs.CRSep 23, 07:18 UTC · Sep 23, 2026Research1

Appears with

GPT-oss-20bai model · 5
Gemma agentproduct · 5
Microsoftorganization · 5
LockBitmalware · 5

Entities are extracted by the model from each article. First seen Sep 23, 2026, last mentioned Sep 23, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.