PCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication
When one AI agent tells another that "the tests passed" or "a person approved this refund", the receiver has only the se
#cs.MA
共收录 117 条相关情报。
← 返回所有主题Is it my preference? Role Grounding Attack against Agent's Memory via Social Interaction
LLM-based agents now share experiences on social platforms and remember new preferences to enhance their performance. Ho
BE-CTDE: Blockchain-Enabled Multi-Agent Reinforcement Learning with Anomaly Detection and Token Economics
Multi-agent reinforcement learning supports cooperative decision-making in Internet of Things systems, but strategic dev
Secure and Functional Code Generation with Self-Evaluation
Large Language Models (LLMs) can generate functionally correct code that remains insecure. Security-focused fine-tuning
Agent-to-Agent Synthetic Social Engineering on the Web
An AI agent can prepare an accurate report and still request an action its user has not authorized. Cooperation across W
Agentic AI Defense: Decode-Time Provenance Binding for MCP
Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted
Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition
In large language model (LLM) steganography, an encoder hides a private message in an otherwise ordinary response, as te
Proof-Carrying Contracts: Commitments AI Agents Cannot Break
AI agents increasingly act on behalf of people or other agents, purchasing services, exchanging information and delegati
Same Data, Different Bytes: Serialization-Invariant Integrity Checks for Agent-Published Datasets
Agent networks require reliable ways for requesting agents to verify where data is located, how it can be accessed, and
The One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents
Can one sentence manipulate an agent's belief by targeting a single implicit warrant linking evidence to a conclusion? I
Red-Teaming Multi-Agent Attacks for Loss-of-Control Risks
AI agents are growing more capable and persistent, and are being deployed in ever larger numbers. As more start collabor
Cryptographically Secure Agent-to-Agent Communication in Multi-Agent Systems
Multi-agent systems (MAS) comprise AI agents that collaborate or compete to perform complex, distributed tasks. Their dy
Provable Authority: A Protocol for Verifiable Authority Resolution and Control Across Human, Organizational, and Agentic Transactions
Payment systems authenticate users, devices, accounts, and cryptographic credentials, but a relying party, such as a cou
From Training to Escalation: Forensic Analysis and Local Recreation of RL/RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)
Mid-2026 reporting on autonomous AI evaluation incidents claimed that frontier large language model (LLM) agents escaped
CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat
AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Cu
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn com
Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems
Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These
From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage
Security operations centers (SOCs) must triage large volumes of alerts, most of which are benign, while missed attacks c
SwarmReconGuard: Black-Box Detection of Distributed Collective Reconnaissance by Individually Benign-Looking Agent Populations
Autonomous and agentic clients can distribute reconnaissance across many identities so that each request remains valid,
Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security
LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial conte