Gradient Band-based Adversarial Training for Generalized Attack Immunity of A3C Path Finding

Chen, Tong; Niu, Wenjia; Xiang, Yingxiao; Bai, Xiaoxuan; Liu, Jiqiang; Han, Zhen; Li, Gang

doi:10.48550/arxiv.1807.06752

Cited by 8 publications

(15 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In another related work, Bai et al [217] also attacked the Deep Q Network (DQN) [218] for robotic path-finding in a white-box setup. Similarly, Chen et al [219] also explored adversarial attacks for the same problem, and devised a so-called Common Dominant Adversarial Examples Generation Method for computing adversarial examples for a given map. In light of their threat models, we can categorize [216], [217] and [219] as white-box attacks within the RL context.…”

Section: B Reinforcement Learningmentioning

confidence: 99%

“…Similarly, Chen et al [219] also explored adversarial attacks for the same problem, and devised a so-called Common Dominant Adversarial Examples Generation Method for computing adversarial examples for a given map. In light of their threat models, we can categorize [216], [217] and [219] as white-box attacks within the RL context. We can also find early instances of black-box attacks for RL.…”

Section: B Reinforcement Learningmentioning

confidence: 99%

See 1 more Smart Citation

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

2018

View full text Add to dashboard Cite

Deep learning is at the heart of the current rise of artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently lead to a large influx of contributions in this direction. This article presents the first comprehensive survey on adversarial attacks on deep learning in Computer Vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

show abstract

Section: B Reinforcement Learningmentioning

confidence: 99%

Section: B Reinforcement Learningmentioning

confidence: 99%

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

2018

View full text Add to dashboard Cite

show abstract

“…Figure 14 depicts a basic depiction of how an adversary can compromise the integrity of the DRL process by adding perturbations to the environment. Chen et al [63] propose a common dominant adversarial examples generation method (CDG) for crafting adversarial examples with high confidence for the environment of DRL. The proposed adversarial attack is tested on A3C trained for pathfinding.…”

Section: Attacks Targeting the Environmentmentioning

confidence: 99%

“…They argue that this resilience in NoisyNets is due to the enhanced generalize-ability and reduced transferability. Chen et al [63] propose a gradient-based adversarial training technique. They use adversarial perturbations generated using their proposed attacking algorithm, i.e., CDG, for re-training the RL agent.…”

Section: A Adversarial Trainingmentioning

confidence: 99%

Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning

Ilahi¹,

Usama²,

Qadir³

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep Reinforcement Learning (DRL) has numerous applications in the real world thanks to its outstanding ability in quickly adapting to the surrounding environments. Despite its great advantages, DRL is susceptible to adversarial attacks, which precludes its use in real-life critical systems and applications (e.g., smart grids, traffic controls, and autonomous vehicles) unless its vulnerabilities are addressed and mitigated. Thus, this paper provides a comprehensive survey that discusses emerging attacks in DRL-based systems and the potential countermeasures to defend against these attacks. We first cover some fundamental backgrounds about DRL and present emerging adversarial attacks on machine learning techniques. We then investigate more details of the vulnerabilities that the adversary can exploit to attack DRL along with the state-of-the-art countermeasures to prevent such attacks. Finally, we highlight open issues and research challenges for developing solutions to deal with attacks for DRL-based intelligent systems.

show abstract

“…The following question thus arises: is there similar adversarial examples that may attack the DRL algorithms in the domain of robot path planning? Some prior work has found the adversarial examples that exist in the process of robot path planning using some DRL algorithms, such as DQN, A3C, and VIN [1,3,10]. From the literature review, we can find some commonalities between the adversarial examples.…”

Section: Introductionmentioning

confidence: 98%

A Training-based Identification Approach to VIN Adversarial Examples

Wang,

Niu,

Chen

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

With the rapid development of Artificial Intelligence (AI), the problem of AI security has gradually emerged. Most existing machine learning algorithms may be attacked by adversarial examples. An adversarial example is a slightly modified input sample that can lead to a false result of machine learning algorithms. The adversarial examples pose a potential security threat for many AI application areas, especially in the domain of robot path planning. In this field, the adversarial examples obstruct the algorithm by adding obstacles to the normal maps, resulting in multiple effects on the predicted path. However, there is no suitable approach to automatically identify them. To our knowledge, all previous work uses manual observation method to estimate the attack results of adversarial maps, which is time-consuming. Aiming at the existing problem, this paper explores a method to automatically identify the adversarial examples in Value Iteration Networks (VIN), which has a strong generalization ability. We analyze the possible scenarios caused by the adversarial maps. We propose a training-based identification approach to VIN adversarial examples by combing the path feature comparison and path image classification. We evaluate our method using the adversarial maps dataset, show that our method can achieve a high-accuracy and faster identification than manual observation method.

show abstract

Gradient Band-based Adversarial Training for Generalized Attack Immunity of A3C Path Finding

Cited by 8 publications

References 2 publications

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning

A Training-based Identification Approach to VIN Adversarial Examples

Contact Info

Product

Resources

About