2 papers
cs.CR2026
Optimizing Agent Planning for Security and Autonomy
Aashish Kolluri, Rishi Sharma, Manuel Costa +5
Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe act…
cs.PL2025
Finding Hyperbugs using Symbolic Execution
Arthur Correnson, Tobias Niessen, Bernd Finkbeiner +1
Many important hyperproperties, such as refinement and generalized non-interference, fall into the class of hyperproperties and require, for each execution trace o…