Sökning: "Fast Gradient Sign Method"

Visar resultat 1 - 5 av 8 uppsatser innehållade orden Fast Gradient Sign Method.

1. 1. Robust Neural Receiver in Wireless Communication : Defense against Adversarial Attacks

   Master-uppsats, Linköpings universitet/Kommunikationssystem

   Författare :Alice Nicklasson Cedbro; [2023]
   Nyckelord :Wireless communication; Neural receiver; Robust neural receiver; Adversarial machine learning; Fast Gradient Sign Method; Adversarial training;

   Sammanfattning : In the field of wireless communication systems, the interest in machine learning has increased in recent years. Adversarial machine learning includes attack and defense methods on machine learning components. LÄS MER

3. 2. Are Distributed Representations in Neural Networks More Robust Against Malicious Fooling Attacks

   Magister-uppsats, Högskolan Dalarna/Institutionen för information och teknik

   Författare :Nida Sardar; Sundas Khan; [2023]
   Nyckelord :Adversarial attacks; Information Smearedness; Artificial Neural Networks; Information Relay; Dropout; Fast Gradient Sign Method;

   Sammanfattning : A plethora of data from sources like IoT, social websites, health, business, and many more have revolutionized the digital world in recent years. To make effective use of data for any sort of analysis, prediction, or automation of applications, the demand for machine learning and artificial intelligence has grown over time. LÄS MER

4. 3. Analysis of Flow Prolongation Using Graph Neural Network in FIFO Multiplexing System

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Weiran Wang; [2023]
   Nyckelord :Network Calculus; Flow Prolongation; Graph Neural Network; Fast Gradient Sign Method; Delay Bound; Nätverkskalkyl; Flödesförlängning; Graph Neural Network; Fast Gradient Sign Method; Fördröjningsgräns;

   Sammanfattning : Network Calculus views a network system as a queuing framework and provides a series of mathematical functions for finding an upper bound of an end-to-end delay. It is crucial for the design of networks and applications with a hard delay guarantee, such as the emerging Time Sensitive Network. LÄS MER

5. 4. The Resilience of Deep Learning Intrusion Detection Systems for Automotive Networks : The effect of adversarial samples and transferability on Deep Learning Intrusion Detection Systems for Controller Area Networks

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Ivo Zenden; [2022]
   Nyckelord :Vehicle Security; Deep Learning; Controller Area Network; Intrusion Detection System; Adversarial Samples; Fordonssäkerhet; Deep Learning; Controller Area Network; Intrusion Detection System; kontradiktoriska prover;

   Sammanfattning : This thesis will cover the topic of cyber security in vehicles. Current vehicles contain many computers which communicate over a controller area network. This network has many vulnerabilities which can be leveraged by attackers. To combat these attackers, intrusion detection systems have been implemented. LÄS MER

7. 5. Deep Reinforcement Learning for Temperature Control in Buildings and Adversarial Attacks

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Kevin Ammouri; [2021]
   Nyckelord :Deep Reinforcement Learning; Adversarial Attacks; Optimal Attacks; Building Control; Optimal Control; Energy Efficiency; Djup förstärkande inlärning; Adversarial Attacker; Optimala Attacker; Byggnadskontroll; Optimal Kontroll; Energieffektivitet;

   Sammanfattning : Heating, Ventilation and Air Conditioning (HVAC) systems in buildings are energy consuming and traditional methods used for building control results in energy losses. The methods cannot account for non-linear dependencies in the thermal behaviour. LÄS MER