The Devil is in the Context: Nine Dimensions of Prompt Injection Attacks
cs.CR
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
- Securing AI Agents with Information-Flow Control
- Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents
- DualView: Preventing Indirect Prompt Injection in Personal AI Agents
- StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection
- LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
- PromptArmor: Simple yet Effective Prompt Injection Defenses
- Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems
- Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
- LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
- The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
- Meta-SecAlign: Training LLMs against Prompt Injection for Robust Agents
- A Framework for Formalizing LLM Agent Security
- Prompt Injection 2.0: Hybrid AI Threats
- The Anatomy of a Prompt Injection: A Component Model for Structured Analysis
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data