ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints

Guesmi, Amira; Khasawneh, Khaled N.; Abu-Ghazaleh, Nael; Alouani, Ihsen

doi:10.1109/ijcnn55064.2022.9892437

Cited by 14 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another measurement that is used to measure the level of compromising the target model integrity by attacks is the Attack Success Rate (ASR). It represents the total number of perturbed dataset inputs in which the adversarial examples cause misclassification by the target model [ 49 ]. This involves classifying the adversarial examples in their target class by the target model [ 50 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

RobEns: Robust Ensemble Adversarial Machine Learning Framework for Securing IoT Traffic

Alkadi,

Al-Ahmadi,

Ben Ismail

2024

Sensors

View full text Add to dashboard Cite

Recently, Machine Learning (ML)-based solutions have been widely adopted to tackle the wide range of security challenges that have affected the progress of the Internet of Things (IoT) in various domains. Despite the reported promising results, the ML-based Intrusion Detection System (IDS) proved to be vulnerable to adversarial examples, which pose an increasing threat. In fact, attackers employ Adversarial Machine Learning (AML) to cause severe performance degradation and thereby evade detection systems. This promoted the need for reliable defense strategies to handle performance and ensure secure networks. This work introduces RobEns, a robust ensemble framework that aims at: (i) exploiting state-of-the-art ML-based models alongside ensemble models for IDSs in the IoT network; (ii) investigating the impact of evasion AML attacks against the provided models within a black-box scenario; and (iii) evaluating the robustness of the considered models after deploying relevant defense methods. In particular, four typical AML attacks are considered to investigate six ML-based IDSs using three benchmarking datasets. Moreover, multi-class classification scenarios are designed to assess the performance of each attack type. The experiments indicated a drastic drop in detection accuracy for some attempts. To harden the IDS even further, two defense mechanisms were derived from both data-based and model-based methods. Specifically, these methods relied on feature squeezing as well as adversarial training defense strategies. They yielded promising results, enhanced robustness, and maintained standard accuracy in the presence or absence of adversaries. The obtained results proved the efficiency of the proposed framework in robustifying IDS performance within the IoT context. In particular, the accuracy reached 100% for black-box attack scenarios while preserving the accuracy in the absence of attacks as well.

show abstract

Section: Methodsmentioning

confidence: 99%

“…A higher attack success rate corresponds to lower adversarial accuracy [ 49 ]. It can be given by the following formula:

…”

Section: Methodsmentioning

confidence: 99%

RobEns: Robust Ensemble Adversarial Machine Learning Framework for Securing IoT Traffic

Alkadi,

Al-Ahmadi,

Ben Ismail

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…In autonomous driving, prior work focused on perception sensor security. In fact, many attacks were proposed with the purpose of jamming cameras [32]- [34], GPS [35], LiDAR [36], [37], RADAR [38], ultrasonic [32] and IMU [39], [40]. Some other works, proposed attacks for regression tasks (e.g., optical flow estimation [41] and depth estimation [1]), and others focused on classification tasks (e.g., 2D object detection and classification [42], [43], tracking [44], traffic light detection [45], and lane detection [46]).…”

Section: Related Workmentioning

confidence: 99%

Bayesian cue integration of structure from motion and CNN-based monocular depth estimation for autonomous robot navigation

Mumuni

2022

Int J Intell Robot Appl

View full text Add to dashboard Cite

In recent years, monocular depth estimation (MDE) has witnessed a substantial performance improvement due to convolutional neural networks (CNNs). However, CNNs are vulnerable to adversarial attacks, which pose serious concerns for safety-critical and security-sensitive systems. Specifically, adversarial attacks can have catastrophic impact on MDE given its importance for scene understanding in applications like autonomous driving and robotic navigation. To physically assess the vulnerability of CNN-based depth prediction methods, recent work tries to design adversarial patches against MDE. However, these methods are not powerful enough to fully fool the vision system in a systemically threatening manner. In fact, their impact is partial and locally limited; they mislead the depth prediction of only the overlapping region with the input image regardless of the target object size, shape and location. In this paper, we investigate MDE vulnerability to adversarial patches in a more comprehensive manner. We propose a novel adaptive adversarial patch (APARATE 1 ) that is able to selectively jeopardize MDE by either corrupting the estimated distance, or simply manifesting an object as disappeared for the autonomous system. Specifically, APARATE is optimized to be shape and scale-aware, and its impact adapts to the target object instead of being limited to the immediate neighborhood. Our proposed patch achieves more than 14 meters mean depth estimation error, with 99% of the target region being affected. We believe this work highlights the threat of adversarial attacks in the context of MDE, and we hope it would alert the community to the real-life potential harm of this attack and motivate investigating more robust and adaptive defenses for autonomous robots.

show abstract

“…Next generation technologies are also used to enhance computing and communications systems. Artificial intelligence (AI) is one of the strong platforms that is very important in developing inventory models in the next generation network [4], [5].…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-powered intelligent reflecting surface systems countering adversarial attacks in machine learning

Muthusamy,

Kannan,

Mani

et al. 2024

IJRES

View full text Add to dashboard Cite

With the increase in the computation power of devices wireless communication has started adopting machine learning (ML) techniques. Intelligent reflecting surface (IRS) is a programmable device that can be used to control electromagnetic wave propagation by changing the electric and magnetic values of its surface. State-of-the-art ML especially on deep learning (DL)-based IRS-enhanced communication is an emerging topic. Yet while integrating IRS with other emerging technologies possibilities of adversarial data creaping is high. Threats to security, their mitigation, and complexes for AI-powered applications in next generation networks are continuously emerging. In this work the ability of an IRS enhanced wireless network in future-generation networks to prevent adversarial machinelearning attacks is studied. The artificial intelligence (AI) model is used to minimize the susceptibility of attacks using defense distillation mitigation technique. The outcome shows that the defensive distillation technique (DDT) increases the strength and performance by around 22% of the AI method under an adversarial attack.

show abstract

ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints

Cited by 14 publications

References 15 publications

RobEns: Robust Ensemble Adversarial Machine Learning Framework for Securing IoT Traffic

RobEns: Robust Ensemble Adversarial Machine Learning Framework for Securing IoT Traffic

Bayesian cue integration of structure from motion and CNN-based monocular depth estimation for autonomous robot navigation

Artificial intelligence-powered intelligent reflecting surface systems countering adversarial attacks in machine learning

Contact Info

Product

Resources

About