Cross-Architecture Robustness of Prompt-Injection Defenses under Adaptive Attack Transfer
A research project that measures whether prompt-injection defenses keep working when both the attack strategy and the agent architecture change...
Tagged: benchmarking
2 ideas with this tag
Reproducible Benchmark Harness for Desktop AI Agents
A research project that builds a reproducible, execution-scored evaluation harness for desktop AI agents — sandboxed environments, scripted task definitions,...