CN111711604A - Wireless network interference attack scene identification method based on distance measurement - Google Patents
Wireless network interference attack scene identification method based on distance measurement Download PDFInfo
- Publication number
- CN111711604A CN111711604A CN202010411555.0A CN202010411555A CN111711604A CN 111711604 A CN111711604 A CN 111711604A CN 202010411555 A CN202010411555 A CN 202010411555A CN 111711604 A CN111711604 A CN 111711604A
- Authority
- CN
- China
- Prior art keywords
- attack
- interference
- interference attack
- scene
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1416—Event detection, e.g. attack signature detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/12—Detection or prevention of fraud
Abstract
The invention discloses a wireless network interference attack scene identification method based on distance measurement, which can accurately classify interference attack scenes. The method for identifying the wireless network interference attack scene comprises the following steps: (10) obtaining an interference attack clustering center: setting different attack scenes, collecting message interaction process data of the node and neighbor nodes for each attack scene to form an offline measurement vector set, and calculating an interference attack clustering center of the attack scene based on the set; (20) on-line measurement vector formation: collecting data of a message interaction process between the node and a neighbor node on line to form an on-line measurement vector; (30) determining an interference attack scene: and calculating the distance from the node online measurement vector to each interference attack clustering center, and outputting an interference attack scene corresponding to the interference attack clustering center with the minimum distance as an identification result.
Description
Technical Field
The invention belongs to the technical field of network data communication, and particularly relates to a wireless network interference attack scene identification method based on distance measurement.
Background
The interference attack is an attack behavior that a legal user uses a wireless channel to receive and transmit a message by sending useless interference signals to the wireless communication channel or destroying the operation process of a wireless network link layer access protocol. According to different behavior strategies, the interference attack can be divided into various attack categories, such as a continuous interference source, a random interference source, a CTS message attack, a DATA message attack, an ACK message attack and the like. The continuous interference source continuously sends useless interference signals to the wireless channel, so that legal users are prevented from accessing the channel; a random interference source sends an interference signal to a channel according to probability, and random switching is carried out between interference initiation and interference stopping; a CTS message attacker monitors RTS messages in a network range, estimates the sending time of the CTS messages, and sends interference signals in the sending process of the CTS messages to cause CTS message collision; a DATA message attacker monitors CTS messages in a network range, estimates the sending time of the DATA messages, and sends interference signals in the sending process of the DATA messages to cause the collision of the DATA messages; an ACK message attacker monitors a DATA message in a network range, estimates the ACK message sending time, and sends an interference signal in the ACK message sending process to cause ACK message collision. Timely and effective interference attack scene identification can provide basis for implementing subsequent anti-interference measures.
In order to identify the type of the interference attack scenario, various methods are currently proposed, including threshold-based detection methods, behavior analysis-based methods, and reputation mechanism-based methods. In the threshold-based method, a normal range of a certain network performance measure needs to be determined through offline data collection, then a threshold is set, and when the observed network performance measure exceeds the threshold, the occurrence of an attack is declared to be detected. In the method based on behavior analysis, a monitoring node is required to observe the behaviors of a network node, such as message forwarding, message discarding, channel occupation and the like, and compare the monitored behaviors with predefined normal behaviors, if the monitored behaviors are not consistent with the predefined normal behaviors, the node is called to be attacked. The method based on the reputation mechanism needs to establish a set of reputation systems in the network in advance, and is used for endowing each node with a corresponding reputation value according to the behavior of the node, and regarding the nodes with the reputation values lower than a specific threshold value as attack nodes. However, the existing method is often difficult to be applied to the classification of various interference attack scenes, and has higher transmission overhead and longer identification time delay.
The existing wireless network interference attack scene identification method cannot solve the problem of classifying multiple types of interference attack scenes at the same time, is difficult to deal with the multiple types of interference attack scenes, and has high cost and low precision.
Disclosure of Invention
The invention aims to provide a wireless network interference attack scene identification method based on distance measurement, which can accurately classify interference attack scenes.
The technical solution for realizing the purpose of the invention is as follows:
a wireless network interference attack scene identification method based on distance measurement comprises the following steps:
(10) obtaining an interference attack clustering center: setting different attack scenes, collecting message interaction process data of the node and neighbor nodes for each attack scene to form an offline measurement vector set, and calculating an interference attack clustering center of the attack scene based on the set;
(20) on-line measurement vector formation: collecting data of a message interaction process between the node and a neighbor node on line to form an on-line measurement vector;
(30) determining an interference attack scene: and calculating the distance from the node online measurement vector to each interference attack clustering center, and outputting an interference attack scene corresponding to the interference attack clustering center with the minimum distance as an identification result.
Compared with the prior art, the invention has the following remarkable advantages:
1. the overhead is small, and the realization is simple. The wireless network interference attack scene recognition method based on distance measurement only needs to classify the interference attack scene according to the message receiving and sending records of the node per se, and does not need to separate interference signals, so that the processing overhead is greatly reduced, and the method is convenient to realize on common wireless equipment.
2. The precision is high, and the estimation is accurate. The invention adopts distance measurement to accurately classify various interference attack scenes, has high classification precision and accurate estimation, and is beneficial to adopting different anti-interference measures.
The invention is described in further detail below with reference to the figures and the detailed description.
Drawings
Fig. 1 is a main flow chart of a wireless network interference attack scene identification method based on distance measurement according to the present invention.
Fig. 2 is a flowchart of the interference attack cluster center acquisition step in fig. 1.
Fig. 3 is a flowchart of the interference attack scenario identification step in fig. 1.
Fig. 4 is an exemplary diagram of a wireless network scenario in the presence of an interference attack.
Detailed Description
As shown in fig. 1, the method for identifying a wireless network interference attack scene based on distance measurement of the present invention includes the following steps:
(10) obtaining an interference attack clustering center: setting different attack scenes, collecting message interaction process data of the node and neighbor nodes for each attack scene to form an offline measurement vector set, and calculating an interference attack clustering center of the attack scene based on the set;
as shown in fig. 2, the step of (10) obtaining the interference attack cluster center includes:
(11) collecting an offline measurement vector set: setting different attack scenes, recording the types and the quantity of messages sent by the node within the interval time delta t at each interval time delta t of each attack scene to form 1 measurement vector, combining the measurement vectors obtained within p interval times delta t into an offline measurement vector set,
wherein the jth measurement vector of the ith interference attack scenario is represented as
m is the total number of types of messages sent,
representing the number of the g type messages sent by the node in the jth interval time, wherein g is more than or equal to 1 and less than or equal to m;
in this embodiment, m is 4, Δ t is 1.5 seconds, the node records the number of RTS, CTS, DATA, and ACK four types of messages sent in 1.5 seconds every 1.5 seconds, and forms 1 4-dimensional vector for the jth measurement of the ith attack scenario
Wherein
And
respectively representing the number of RTS, CTS, DATA and ACK messages sent by the node in the jth 1.5 second interval. Taking p as 6, the node forms a training sample set containing 6 measure vectors for the ith attack scene
Taking 5 attack scenes and adding non-interference attack scenes to form an offline measurement vector set { S } of n-6 scenes1,S2,…,S6}。
(12) And (3) calculating an interference attack clustering center: the interference attack clustering centers corresponding to the interference attack scenes form a clustering center set { C1,C2,…,Ci,…,CnN is the total number of attack scenarios;
interference attack clustering center C of ith attack sceneiCalculated as follows:
in the formula, j represents a measure vector obtained at the jth interval time of the ith attack scene, and j is more than or equal to 1 and less than or equal to p;
in this embodiment, taking n to 6, the node calculates 6 measure sets S respectively1、S2、S3、S4、S5And S6The cluster center C of each measure vector set1、C2、C3、C4、C5And C6。
(20) On-line measurement vector formation: collecting data of a message interaction process between the node and a neighbor node on line to form an on-line measurement vector;
the (20) online measurement vector forming step specifically comprises:
under the scene of unknown interference attack, at each interval time delta t, the types and the number of the messages sent by the node within the interval time delta t are recorded to form 1 measurement vector r ═ r (r ═ r)1,…,rm) Where m is the total number of types of messages sent.
In this embodiment, if m is 4 and Δ t is 1.5 seconds, the node collects the number of RTS, CTS, DATA, and ACK four types of messages sent by itself every 1.5 seconds, and forms 1 4-dimensional vector r (r is r)1,r2,r3,r4) Wherein r is1、r2、r3And r4Respectively representing the number of RTS, CTS, DATA and ACK messages sent by the node in the past 1.5 seconds.
(30) Determining an interference attack scene: and calculating the distance from the node online measurement vector to each interference attack clustering center, and outputting an interference attack scene corresponding to the interference attack clustering center with the minimum distance as an identification result.
As shown in fig. 3, the (30) interference attack scenario determination step includes:
(31) calculating the clustering center distance: for a plurality of interference attack scenes, an online measurement vector r is calculated according to the following formula (r ═ r)1,…,rm) Interference attack clustering center C for ith interference attack sceneiDistance d ofi：
di＝(r1-Ci1)2+…+(rm-Cim)2，1≤i≤n；
(32) And (3) interference attack scene identification: and comparing the distances from the online measurement vectors to the interference attack clustering centers corresponding to the interference attack scenes, and taking the interference attack scene corresponding to the interference attack clustering center corresponding to the minimum distance value as the detected interference attack scene.
Fig. 4 is an exemplary diagram of a wireless network scenario in which an interference source is present. In fig. 4, 64 nodes are deployed in an area of 2000 meters by 2000 meters, the transmission power of an interference source is set to 15dBm, and a free space propagation model is adopted. Each circle represents 1 radio network node, the numbering of which is also shown in fig. 4. When two nodes can communicate, there is a link between them, represented as a line segment in fig. 4. For the scenario shown in fig. 4, node 27 is the source of interference and has coordinates (540,849). The coordinates of the node 26 are (409,981), and the interference attack recognition method based on the distance measurement is adopted to recognize the interference attack of the interference source shown by the five-pointed star under 6 scenes. The 6 scenes are respectively an interference-free attack, a continuous interference source, a random interference source, a CTS message attack, a DATA message attack and an ACK message attack.
In this embodiment, n is 6, m is 4, p is 6, Δ t is 1.5 seconds, the maximum number of retransmissions of the packet is 5, and the size of the initial contention window is 15. The node 26 collects the number of RTS, CTS, DATA, and ACK four types of messages sent by itself every 1.5 seconds.
In (10) the step of acquiring the offline data and the step of acquiring the interference attack clustering center, and in (11) the step of collecting the offline measurement vector sets, the node 26 obtains 6 measurement vector sets for 6 scenes, which are respectively as follows:
an interference-free attack scene: s1＝{(599,145,110,27)，(543,178,107,42)，(353,119,59,25)，(523,237,90,65)，(572,162,97,46)，(344,175,72,37)}。
Persistent interferer scenarios: s2＝{(0,0,0,0)，(0,0,0,0)，(0,0,0,0)，(0,0,0,0)，(0,0,0,0)，(0,0,0,0)}。
Random interference source scenario: s3＝{(281,84,39,10)，(284,89,57,14)，(171,57,33,11)，(254,77,43,14)，(264,67,42,19)}，(197,53,35,11)}。
CTS message attack scenario: s4＝{(514,0,24,0)，(579,0,35,0)，(433,0,25,0)，(606,0,39,0)，(576,0,41,0)，(433,0,35,0)}。
DATA message attack scenario: s5＝{(509,124,0,11)，(505,124,0,14)，(346,74,0,2)，(581,125,0,17)，(490,117,0,8)，(378,80,0,3)}。
An ACK message attack scene: s6＝{(572,143,103,0)，(499,131,96,0)，(381,92,59,0)，(536,128,91,0)，(543,124,103,0)，(408,90,77,0)}。
In the step (12) of calculating the cluster centers, the cluster centers calculated by the node 26 are:
an interference-free attack scene: c1＝(489.0000,169.3333,89.1667,40.3333)；
Persistent interferer scenarios: c2＝(0,0,0,0)；
Random interference source scenario: c3＝(241.8333,71.1667,41.5000,13.1667)；
CTS message attack scenario: c4＝(523.5000,0,33.1667,0)；
DATA message attack scenario: c5＝(468.1667,107.3333,0,9.1667)；
An ACK message attack scene: c6＝(489.8333,118.0000,88.1667,0)；
The node 26 obtains a plurality of groups of online measurement vectors in the online measurement vector forming step (20), and performs clustering center distance calculation and interference attack scene identification in the interference attack scene determining step (30). For example:
in a scene without a source of interference, after obtaining an online measurement vector r ═ 605,170,99,37, the calculated cluster center distances are respectively: d1＝1356,d2＝40610,d3＝14553,d4＝4125,d5＝3323,d6The identified attack type is a non-interfering source, consistent with a true attack type 1745.
In a continuous interference source scene, after an online measurement vector r is obtained as (0,0,0,0), the calculated cluster center distances are respectively: d1＝27737,d2＝0,d3＝6544,d4＝27515,d5＝23078,d626163, the identified attack type is a persistent interferer, consistent with the true attack type.
In a random interference source scene, after obtaining an online measurement vector r ═ (267,82,40,14), the cluster center distances obtained by calculation are respectively: d1＝60022,d2＝79809,d3＝754,d4＝72759,d5＝42733,d653467, the identified attack type is a random interference source, which coincides with the true attack type.
In a CTS message attack scenario, after an online measurement vector r is obtained as (566,0,45,0), the calculated cluster center distances are respectively: d1＝3818,d2＝32238,d3＝11033,d4＝195,d5＝2320,d62159, the identified attack type is CTS message attack and is consistent with the real attack type.
In a DATA message attack scene, after an online measurement vector r is obtained (585,108,0,7), the calculated cluster center distances are respectively: d1＝2204,d2＝35394,d3＝12088,d4＝1660,d5＝1366,d61698, the identified attack type is DATA message attack, which is consistent with the real attack type.
In an ACK message attack scene, after an online measurement vector r is obtained as (537,131,89,0), the cluster center distances obtained by calculation are respectively: d1＝540,d2＝3.1345,d3＝9313,d4＝2046,d5＝1330,d6239, the identified attack type is an ACK packet attack, which is consistent with the real attack type.
It can be seen that the wireless network interference attack type identified by the method of the invention is consistent with the actual type.
The invention only needs to identify the interference attack scene according to the message receiving and sending records of the node per se, and does not need to separate interference signals, thereby greatly reducing the processing overhead and being convenient to realize on common wireless equipment. The invention provides an interference attack scene identification method using distance measurement, and high identification precision is obtained.
Claims (4)
1. A wireless network interference attack scene identification method based on distance measurement is characterized by comprising the following steps:
(10) obtaining an interference attack clustering center: setting different attack scenes, collecting message interaction process data of the node and neighbor nodes for each attack scene to form an offline measurement vector set, and calculating an interference attack clustering center of the attack scene based on the set;
(20) on-line measurement vector formation: collecting data of a message interaction process between the node and a neighbor node on line to form an on-line measurement vector;
(30) determining an interference attack scene: and calculating the distance from the node online measurement vector to each interference attack clustering center, and outputting an interference attack scene corresponding to the interference attack clustering center with the minimum distance as an identification result.
2. The method for identifying wireless network interference attack scenarios according to claim 1, wherein the step of (10) obtaining the interference attack clustering center comprises:
(11) collecting an offline measurement vector set: setting different attack scenes, recording the types and the quantity of messages sent by the node within the interval time delta t at each interval time delta t of each attack scene to form 1 measurement vector, combining the measurement vectors obtained within p interval times delta t into an offline measurement vector set,
wherein the jth measurement vector of the ith interference attack scenario is represented as
m is the total number of types of messages sent,
representing the number of the g type messages sent by the node in the jth interval time, wherein g is more than or equal to 1 and less than or equal to m;
(12) and (3) calculating an interference attack clustering center: the interference attack clustering centers corresponding to the interference attack scenes form a clustering center set { C1,C2,…,Ci,…,CnN is the total number of attack scenarios;
interference attack clustering center C of ith attack sceneiCalculated as follows:
in the formula, j represents a measure vector obtained at the jth interval time of the ith attack scene, and j is more than or equal to 1 and less than or equal to p.
3. The method for identifying wireless network interference attack scenes according to claim 2, wherein the step of (20) forming the online measurement vector specifically comprises:
under the scene of unknown interference attack, at each interval time delta t, the types and the number of the messages sent by the node within the interval time delta t are recorded to form 1 measurement vector r ═ r (r ═ r)1,…,rm) Where m is the total number of types of messages sent.
4. The wireless network interference attack scenario recognition method of claim 3, wherein the (30) interference attack scenario determination step comprises:
(31) calculating the clustering center distance: for a plurality of interference attack scenes, an online measurement vector r is calculated according to the following formula (r ═ r)1,…,rm) Interference attack clustering center C for ith interference attack sceneiDistance d ofi：
di＝(r1-Ci1)2+…+(rm-Cim)2，1≤i≤n；
(32) And (3) interference attack scene identification: and comparing the distances from the online measurement vectors to the interference attack clustering centers corresponding to the interference attack scenes, and taking the interference attack scene corresponding to the interference attack clustering center corresponding to the minimum distance value as the detected interference attack scene.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010411555.0A CN111711604B (en) | 2020-05-15 | 2020-05-15 | Wireless network interference attack scene identification method based on distance measurement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010411555.0A CN111711604B (en) | 2020-05-15 | 2020-05-15 | Wireless network interference attack scene identification method based on distance measurement |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111711604A true CN111711604A (en) | 2020-09-25 |
| CN111711604B CN111711604B (en) | 2022-02-18 |
Family
ID=72537763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010411555.0A Active CN111711604B (en) | 2020-05-15 | 2020-05-15 | Wireless network interference attack scene identification method based on distance measurement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111711604B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE2508391A1 (en) * | 1974-02-27 | 1975-08-28 | Magnusson Arnold Ingemar | MULTIPLE LAUNCH DEVICE |
| US7020701B1 (en) * | 1999-10-06 | 2006-03-28 | Sensoria Corporation | Method for collecting and processing data using internetworked wireless integrated network sensors (WINS) |
| CN105430685A (en) * | 2015-11-05 | 2016-03-23 | 中国人民解放军总参谋部第六十三研究所 | Interference source number estimation method based on control chart |
| CN105554762A (en) * | 2015-12-10 | 2016-05-04 | 广东工业大学 | RSS-based wireless spoofing attack positioning method |
| CN106899435A (en) * | 2017-02-21 | 2017-06-27 | 浙江大学城市学院 | A kind of complex attack identification technology towards wireless invasive detecting system |
| CN109787979A (en) * | 2019-01-22 | 2019-05-21 | 电子科技大学 | A kind of detection method of electric power networks event and invasion |
| CN109862016A (en) * | 2019-02-19 | 2019-06-07 | 电子科技大学 | A kind of countercheck for the automatic dilatation Yo-Yo attack of cloud computing |
| CN109981672A (en) * | 2019-04-03 | 2019-07-05 | 电子科技大学 | A kind of multi-intrusion detection method based on semi-supervised clustering |
| CN110460575A (en) * | 2019-07-11 | 2019-11-15 | 珠海市鸿瑞信息技术股份有限公司 | One kind can be realized security audit functional network Security Situation Awareness Systems |
-
2020
- 2020-05-15 CN CN202010411555.0A patent/CN111711604B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE2508391A1 (en) * | 1974-02-27 | 1975-08-28 | Magnusson Arnold Ingemar | MULTIPLE LAUNCH DEVICE |
| US7020701B1 (en) * | 1999-10-06 | 2006-03-28 | Sensoria Corporation | Method for collecting and processing data using internetworked wireless integrated network sensors (WINS) |
| CN105430685A (en) * | 2015-11-05 | 2016-03-23 | 中国人民解放军总参谋部第六十三研究所 | Interference source number estimation method based on control chart |
| CN105554762A (en) * | 2015-12-10 | 2016-05-04 | 广东工业大学 | RSS-based wireless spoofing attack positioning method |
| CN106899435A (en) * | 2017-02-21 | 2017-06-27 | 浙江大学城市学院 | A kind of complex attack identification technology towards wireless invasive detecting system |
| CN109787979A (en) * | 2019-01-22 | 2019-05-21 | 电子科技大学 | A kind of detection method of electric power networks event and invasion |
| CN109862016A (en) * | 2019-02-19 | 2019-06-07 | 电子科技大学 | A kind of countercheck for the automatic dilatation Yo-Yo attack of cloud computing |
| CN109981672A (en) * | 2019-04-03 | 2019-07-05 | 电子科技大学 | A kind of multi-intrusion detection method based on semi-supervised clustering |
| CN110460575A (en) * | 2019-07-11 | 2019-11-15 | 珠海市鸿瑞信息技术股份有限公司 | One kind can be realized security audit functional network Security Situation Awareness Systems |
Non-Patent Citations (4)
| Title |
|---|
| H. LIU等: ""Localizing Multiple Jamming Attackers in Wireless Networks"", 《2011 31ST INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS, 2011》 * |
| T. WANG等: ""GSA-Based Jammer Localization in Multi-Hop Wireless Network"", 《2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE) AND IEEE INTERNATIONAL CONFERENCE ON EMBEDDED AND UBIQUITOUS COMPUTING (EUC)》 * |
| 凡云华: ""无线传感器网络干扰攻击及干扰源定位技术研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 王棋萍 等: ""基于接收干扰信号强度估计的干扰源定位算法"", 《军事通信技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111711604B (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9503465B2 (en) | Methods and apparatus to identify malicious activity in a network | |
| Kosmanos et al. | Intrusion detection system for platooning connected autonomous vehicles | |
| CN109151707B (en) | Sight distance/non-sight distance path identification method in moving state | |
| Liu et al. | A research on CSI-based human motion detection in complex scenarios | |
| CN107607916B (en) | Self-defense type speed and distance joint deception jamming resisting method | |
| CN103916860B (en) | Outlier data detection method based on space time correlation in wireless senser cluster l network | |
| CN112291107B (en) | Network analysis program, network analysis device, and network analysis method | |
| CN110475246B (en) | Malicious anchor node detection method based on isolated forest and sequential probability ratio detection | |
| Panichpapiboon et al. | Evaluation of a neighbor-based vehicle density estimation scheme | |
| CN114422379B (en) | Analysis method for multi-platform equipment wireless networking | |
| CN110649982B (en) | Double-threshold energy detection method based on secondary user node selection | |
| CN111817803A (en) | Frequency spectrum sensing method and system based on correlation coefficient and K-means clustering algorithm and computer readable storage medium | |
| CN111711604B (en) | Wireless network interference attack scene identification method based on distance measurement | |
| CN111600877A (en) | LDoS attack detection method based on MF-Ada algorithm | |
| CN101917732A (en) | Wireless flow judging method | |
| Tang et al. | Real-time detection of selfish behavior in IEEE 802.11 wireless networks | |
| Fernandes et al. | An adaptive recurrent neural network model dedicated to opportunistic communication in wireless networks | |
| Scalabrin et al. | Machine learning based network analysis using millimeter-wave narrow-band energy traces | |
| CN112367311B (en) | DDoS attack detection method, device, equipment and storage medium | |
| Hu et al. | Protecting platoons from stealthy jamming attack | |
| CN114172704B (en) | Abnormal node detection method based on space-time relation of BSM data packet | |
| CN113608211B (en) | Radar networking mode identification method based on communication traffic information assistance | |
| CN113453269B (en) | Priority-based channel load statistics and backoff window setting method | |
| Mukasa et al. | Hidden Node Recognition Utilizing Wireless LAN Sensing Data in Indoor Environments | |
| Ito et al. | High-sensitivity detection method for signals in PhyC-SN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |