应用强化学习来保护深度神经网络免受软错误的影响
Peng Su1, Yuhang Li1, Zhonghai Lu2
1Department of Engineering Design, KTH Royal Institute of Technology, 10044 Stockholm, Sweden.
Sensors (Basel, Switzerland)
|July 12, 2025
概括
这项研究引入了一种新的强化学习方法,通过识别和掩盖易受攻击的位来保护深度神经网络免受软错误的影响,从而显著提高了系统的稳定性和安全性.
科学领域:
- 人工智能的人工智能
- 计算机科学 计算机科学
- 电气工程 电气工程
背景情况:
- 深度神经网络 (DNN) 对基于传感器的系统至关重要,但容易发生软错误,威胁到系统安全.
- 传统的容错方法在复杂的DNN架构中面临着可扩展性挑战.
- 确保DNN对错误的稳定性对于可靠的AI应用程序至关重要.
研究的目的:
- 开发一种有效和可扩展的方法来保护DNN免受软错误.
- 使用一种新的方法,在DNN中识别和减轻脆弱位.
- 为了提高人工智能驱动的传感器系统的安全性和可靠性.
主要方法:
- 开发了一个基于强化学习 (RL) 的代理来识别DNN中的脆弱位.
- 使用故障注入模拟来分析层层的网络弹性.
- 转移学习被用于有效合成和部署比特面具.
主要成果:
- 提出的基于RL的方法显示,与基线技术相比,显著提高了性能 (10-15%).
- 易受攻击的位被动态和高效地保护,提高了网络的稳定性.
- 这种方法在保护选定的神经网络免受软错误时被证明是有效的.
结论:
- 与传统方法相比,基于RL的方法为保护DNN免受软错误提供了优越的解决方案.
- 这种技术通过减轻软错误影响来提高人工智能系统的安全性和可靠性.
- 该方法提供了一种可扩展和有效的方式来提高DNN的弹性.
相关概念视频
Avoidance Learning and Learned Helplessness
1.9K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
1.9K
Observational Learning
317
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
317
Neural Regulation
40.2K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
40.2K
Reinforcement
347
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
347
Survival Tree
164
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
164
Types of Errors: Detection and Minimization
2.4K
Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
2.4K

