Similar Items: Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents
- ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
- IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection
- FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
- Cryptographic Registry Provenance: Structural Defense Against Dependency Confusion in AI Package Ecosystems
- PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
- Autonomous LLM Agent Worms: Cross-Platform Propagation, Automated Discovery and Temporal Re-Entry Defense