Self-Healing Robust Neural Networks via Closed-Loop Control
Despite the wide applications of neural networks, there have been increasing concerns about their vulnerability issue. While numerous attack and defense techniques have been developed, this work investigates the robustness issue from a new angle: can we design a self-healing neural network that can automatically detect and fix the vulnerability issue by itself? A typical self-healing mechanism is the immune system of a human body. This biology-inspired idea has been used in many engineering designs but is rarely investigated in deep learning. This paper considers the post-training self-healing of a neural network, and proposes a closed-loop control formulation to automatically detect and fix the errors caused by various attacks or perturbations. We provide a margin-based analysis to explain how this formulation can improve the robustness of a classifier. To speed up the inference of the proposed self-healing network, we solve the control problem via improving the Pontryagin Maximum Principle-based solver. Lastly, we present an error estimation of the proposed framework for neural networks with nonlinear activation functions. We validate the performance on several network architectures against various perturbations. Since the self-healing method does not need a-priori information about data perturbations/attacks, it can handle a broad class of unforeseen perturbations.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SHIELD: An Auto-Healing Agentic Defense Framework for LLM Resource Exhaustion Attacks
Sponge attacks increasingly threaten LLM systems by inducing excessive computation and DoS. Existing defenses either rely on statistical filters that fail on semantically meaningful attacks or use static LLM-based detect…
Semantic SimilaritySelf-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems
Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery. In these systems, failures arise not only from model e…
Efficient Coordination with the System-Level Shared State: An Embodied-AI Native Modular Framework
As Embodied AI systems move from research prototypes to real world deployments, they tend to evolve rapidly while remaining reliable under workload changes and partial failures. In practice, many deployments are only par…
Feedforward Control of DGs for a Self-healing Microgrid
Network reconfiguration (NR) has recently received significant attention due to its potential to improve grid resilience by realizing self-healing microgrids (MGs). This paper proposes a new strategy for the real-time fr…
Reinforcement Learning for Self-Healing Material Systems
The transition to autonomous material systems necessitates adaptive control methodologies to maximize structural longevity. This study frames the self-healing process as a Reinforcement Learning (RL) problem within a Mar…
Reinforcement Learning