Adversarial and Clean Data Are Not Twins

Gong, Zhitao; Wang, Wenlu; Ku, Wei‐Shinn

doi:10.1145/3593078.3593935

Cited by 54 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach is based on ML models to detect AEs. Gong et al [13] proposed a method based on a binary classifier trained independently from the original model. They trained the binary classifier to output 0 for the clean data and 1 for the AEs.…”

Section: Related Workmentioning

confidence: 99%

“…Gong et al [13] Detect AEs by a binary classifier that is trained independently from the original model.…”

Section: Yes No Nomentioning

confidence: 99%

“…By detecting the sensors used in the attack, we can check the sensors and replace them. Many methods to detect AEs have also been proposed [13][14][15][16][17][18][19][20]. Hendrycks and Gimpel introduced detection methods for adversarial examples based on identifying implausible gradients [16,17].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Sensors Used for Adversarial Examples against Machine Learning Models

Kurniawan,

Ohsita,

Maisuria

et al. 2023

Preprint

View full text Add to dashboard Cite

Machine learning (ML) systems that use sensors obtain observations from sensors and use them to recognize and interpret the current situation. These systems are susceptible to sensor-based adversarial example attacks (AEs); if some sensors are vulnerable and can be compromised by an attacker, the attacker can change the output of the system by changing the values of the sensors. The detection of compromised sensors is important to defend the system against sensor-based AEs, because we can check the sensors and replace them by detecting the sensors used by the attacker. In this paper, we propose a method to detect the sensors used in sensor-based AEs by utilizing the features of the attack that cannot be avoided. In this method, we introduced a model called the feature-removable model (FRM), which allows us to select the features used as inputs into the model. Our method detects the sensors used in sensor-based AEs by finding the inconsistencies between the outputs of the FRM obtained by changing the selected features. We evaluated our method using a human activity recognition model with sensors attached to the user’s chest, wrist, and ankle. We demonstrate that our method can accurately detect sensors used by the attacker and achieves an average Recall of Detection of 0.92, and the average Precision of Detection is 0.72.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Gong et al [13] Detect AEs by a binary classifier that is trained independently from the original model.…”

Section: Yes No Nomentioning

confidence: 99%

See 1 more Smart Citation

Detection of Sensors Used for Adversarial Examples against Machine Learning Models

Kurniawan,

Ohsita,

Maisuria

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Clustering-based attack detection for adversarial reinforcement learning

Majadas,

García,

Fernández

2024

Appl Intell

View full text Add to dashboard Cite

Detecting malicious attacks presents a major challenge in the field of reinforcement learning (RL), as such attacks can force the victim to perform abnormal actions, with potentially severe consequences. To mitigate these risks, current research focuses on the enhancement of RL algorithms with efficient detection mechanisms, especially for real-world applications. Adversarial attacks have the potential to alter the environmental dynamics of a Markov Decision Process (MDP) perceived by an RL agent. Leveraging these changes in dynamics, we propose a novel approach to detect attacks. Our contribution can be summarized in two main aspects. Firstly, we propose a novel formalization of the attack detection problem that entails analyzing modifications made by attacks to the transition and reward dynamics within the environment. This problem can be framed as a context change detection problem, where the goal is to identify the transition from a “free-of-attack” situation to an “under-attack” scenario. To solve this problem, we propose a groundbreaking “model-free” clustering-based countermeasure. This approach consists of two essential steps: first, partitioning the transition space into clusters, and then using this partitioning to identify changes in environmental dynamics caused by adversarial attacks. To assess the efficiency of our detection method, we performed experiments on four established RL domains (grid-world, mountain car, carpole, and acrobot) and subjected them to four advanced attack types. Uniform, Strategically-timed, Q-value, and Multi-objective. Our study proves that our technique has a high potential for perturbation detection, even in scenarios where attackers employ more sophisticated strategies.

show abstract

A state-of-the-art review on adversarial machine learning in image classification

Bajaj

Vishwakarma

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Adversarial and Clean Data Are Not Twins

Cited by 54 publications

References 5 publications

Detection of Sensors Used for Adversarial Examples against Machine Learning Models

Detection of Sensors Used for Adversarial Examples against Machine Learning Models

Clustering-based attack detection for adversarial reinforcement learning

A state-of-the-art review on adversarial machine learning in image classification

Contact Info

Product

Resources

About