Search papers, labs, and topics across Lattice.
This paper introduces HARD, a self-evolving runtime defense framework designed for large language model (LLM) agents that automates the identification and improvement of security interventions based on observed failure traces. By formulating a harness-level perspective on runtime defenses, the authors provide a systematic characterization that unifies existing interventions and facilitates the autonomous evolution of defense mechanisms. Experimental results show that HARD significantly enhances security performance compared to traditional handcrafted defenses while maintaining the utility of benign tasks.
Autonomous defense evolution could redefine how we secure LLM agents against sophisticated threats, outperforming traditional methods.
The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses rely heavily on manually designed interventions and lack a principled framework for their construction and maintenance. In this work, we first develop a harness-level formulation of runtime defense that systematically characterizes how harness mechanisms enable defense construction and provides a unified view of existing runtime defense interventions from a harness perspective. Building on this formulation, we propose HARD (Harness-based Autonomous Runtime Defense Evolution), a self-evolving runtime defense framework that automatically identifies appropriate intervention strategies and iteratively improves defense artifacts based on observed failure traces. HARD transforms runtime defense development from manual engineering into an autonomous evolution process, and extensive experiments demonstrate that it improves security performance over existing handcrafted defenses while preserving benign task utility. Our findings highlight autonomous defense evolution as a promising new paradigm for securing deployed LLM agents, enabling agents to identify defense weaknesses and continuously improve their protection mechanisms.
