Distributed Detection of Malicious Attacks on Consensus Algorithms with Applications in Power Networks

Patel, Sourav; Khatana, Vivek; Saraswat, Govind; Salapaka, Murti V.

doi:10.1109/codit49905.2020.9263882

Cited by 8 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [13], the decision score is computed by a temporal difference strategy to detect and isolate attackers. Similar score-based methods are also shown in [23]- [25]. While such methods have reasonable performance, the score design is somewhat ad-hoc and relies heavily on the experts to design sophisticated decision functions, and the detection thresholds of these score-based methods need to be adjusted judiciously.…”

Section: Introductionmentioning

confidence: 92%

See 1 more Smart Citation

Detection of Insider Attacks in Distributed Projected Subgradient Algorithms

Wu¹,

Li²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

The gossip-based distributed algorithms are widely used to solve decentralized optimization problems in various multi-agent applications, while they are generally vulnerable to data injection attacks by internal malicious agents as each agent locally estimates its decent direction without an authorized supervision. In this work, we explore the application of artificial intelligence (AI) technologies to detect internal attacks. We show that a general neural network is particularly suitable for detecting and localizing the malicious agents, as they can effectively explore nonlinear relationship underlying the collected data. Moreover, we propose to adopt one of the state-of-art approaches in federated learning, i.e., a collaborative peer-topeer machine learning protocol, to facilitate training our neural network models by gossip exchanges. This advanced approach is expected to make our model more robust to challenges with insufficient training data, or mismatched test data. In our simulations, a least-squared problem is considered to verify the feasibility and effectiveness of AI-based methods. Simulation results demonstrate that the proposed AI-based methods are beneficial to improve performance of detecting and localizing malicious agents over score-based methods, and the peer-to-peer neural network model is indeed robust to target issues.

show abstract

Section: Introductionmentioning

confidence: 92%

“…where L i (W ) = 1 q ς∈Di (W , ς). This formulation enables us to state the optimization problem (25) in a distributed manner. This distributed collaborative training problem could be addressed by gossip exchanges [41], [42].…”

Section: A the Distributed Collaborative Training Processmentioning

confidence: 99%

Detection of Insider Attacks in Distributed Projected Subgradient Algorithms

Wu¹,

Li²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The several projects are funded by the different countries in spite of economic problems for the renewable energy sources connection to the power grids. The different energy sources are combined in the SSG like small wind turbines, and integration of the micro turbines with storage devices, like batteries connected at low voltage systems [7,8]. For electric power distribution, there is installation of the different protection systems at every feeder.…”

Section: Introductionmentioning

confidence: 99%

Research on Multi-Agent Systems in a Smart Small Grid for Resource Apportionment and Planning

Yang

Paúl

2021

SCPE

View full text Add to dashboard Cite

With the advancement in the technology, deployment of sensors in the industrial or public building is increasing rapidly. The basic aim is to obtain the data from the environment and decision making to the energy saving. The activities caused by the human results the undergoing negative change in the environment. There are many techniques available for decision making and consider the environmental factors solely which cause the energy consumption. However, user’s preferences are not adapted by the systems, but at energy consumption optimization, these systems are very successful. The end-users use the system which considers the factors and their wellbeing are get affected. The distributed generation is incorporated by the Smart Small Grid (SSG), communication network and the sensors for the more reliable, flexible and efficient grid. The energy saving system is presented in this paper which also adapts to the inhabitants preferences apart from environmental conditions consideration. The architecture of Multi-Agent System (MAS) and the agents are utilized for negotiation process performance between the users comfort preferences and optimization degree that according to these preferences, achievement of system is done. The energy consumption of 40% is obtained and in the inhabitants' behavior pattern, the algorithm was specialized. The 16.89% of reduction is obtained by the existing system and it was focused to obtain the agreement between the system and users for user preference satisfaction and the energy optimization is also performed at the same time.

show abstract

“…These applications need sharing of a high dimensional parameter vector, usually of the order of 32 × 32 × 3 ∼ 1024 × 1024 × 3. Applications such as spectrum sensing in Ad hoc cognitive radio networks, see [21], distributed detection of malicious attacks in finitetime consensus networks [22] and control of autonomous agents like unmanned aerial vehicles (UAVs) for search and survey operations, see [10] also depend on implementing higher dimensional consensus protocols.…”

Section: Introductionmentioning

confidence: 99%

Convex Decreasing Algorithms: Distributed Synthesis and Finite-time Termination in Higher Dimension

Melbourne¹,

Saraswat²,

Khatana³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

We introduce a general mathematical framework for distributed algorithms, and a monotonicity property frequently satisfied in application. These properties are leveraged to provide finite-time guarantees for converging algorithms, suited for use in the absence of a central authority. A central application is to consensus algorithms in higher dimension. These pursuits motivate a new peer to peer convex hull algorithm which we demonstrate to be an instantiation of the described theory. To address the diversity of convex sets and the potential computation and communication costs of knowing such sets in high dimension, a lightweight norm based stopping criteria is developed. More explicitly, we give a distributed algorithm that terminates in finite time when applied to consensus problems in higher dimensions and guarantees the convergence of the consensus algorithm in norm, within any given tolerance. Applications to consensus least squared estimation and distributed function determination are developed. The practical utility of the algorithm is illustrated through MATLAB simulations.

show abstract

Distributed Detection of Malicious Attacks on Consensus Algorithms with Applications in Power Networks

Cited by 8 publications

References 13 publications

Detection of Insider Attacks in Distributed Projected Subgradient Algorithms

Detection of Insider Attacks in Distributed Projected Subgradient Algorithms

Research on Multi-Agent Systems in a Smart Small Grid for Resource Apportionment and Planning

Convex Decreasing Algorithms: Distributed Synthesis and Finite-time Termination in Higher Dimension

Contact Info

Product

Resources

About