Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents
cs.CR, cs.AI
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: under submission, mega paper (authorship does not imply endorsement of every sub-section)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Differentially Private Sparse Vectors with Low Error, Optimal Space, and Fast Access
- MAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security
- Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
- Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities
- Agent Security is a Systems Problem
- Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents
- Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
- Practice-Informed, Practice-Ready: An AI security incident taxonomy
- Multi-Agent Risks from Advanced AI
- Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
- A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
- AI Agents Under EU Law
- Web Agents Should Adopt the Plan-Then-Execute Paradigm
- AI Risk Management Should Incorporate Both Safety and Security
- Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs