Similar Items: 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
- Static Attribution of Android Residential Proxy Malware Using Graph Kernels
- ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
- Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation
- AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
- Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours