The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI
Om Narayan, Ramkinker Singh, Praveen Baskar
cs.AI, cs.CR
Submitted: 2026-07-20
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Toolformer: Language Models Can Teach Themselves to Use Tools
- ReAct: Synergizing Reasoning and Acting in Language Models
- MemGPT: Towards LLMs as Operating Systems
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
- Memory Injection Attacks on LLM Agents via Query-Only Interaction
- MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Many-to-One Adversarial Consensus: Exposing Multi-Agent Collusion Risks in AI-Based Healthcare
- EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- From Grounding to Planning: Benchmarking Bottlenecks in Web Agents
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- World of Workflows: A Benchmark for Bringing World Models to Enterprise Systems
- AgentBench: Evaluating LLMs as Agents
- AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
- Enforcing Temporal Constraints for LLM Agents
- AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
- A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
- Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection