Sökning: "Adversarial Attack Detection"

Visar resultat 1 - 5 av 7 uppsatser innehållade orden Adversarial Attack Detection.

  1. 1. AI for Cybersecurity : A Study on Machine Learning and DoS Attacks AI Robustness and Bypassing Detection Methods

    Kandidat-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Molin Matti; Böhme Fredrik; [2023]
    Nyckelord :AI; Cybersecurity; Machine learning; DoS; Poisoning; AI; Cybersäkerhet; Maskininlärning; DoS; Poisoning;

    Sammanfattning : Cybercrime has increased for several years; both in volume andsophistication. When the capabilities of threat actors increase, techniques andtactics within cybersecurity also need to evolve. AI and machine learninghave potential to prevent and mitigate attacks. LÄS MER

  3. 2. Anomalous Behavior Detection in Aircraft based Automatic Dependent Surveillance–Broadcast (ADS-B) system using Deep Graph Convolution and Generative model (GA-GAN)

    Magister-uppsats, Linköpings universitet/Databas och informationsteknik

    Författare :Jayesh Kenaudekar; [2022]
    Nyckelord :Intrusion detection aircraft aviation security adsb protocol AI deep learning machine learning graph generative model surveillance broadcast;

    Sammanfattning : The Automatic Dependent Surveillance-Broadcast (ADS-B) is a key component of the Next Generation Air Transportation System (Next Gen) that manages the increasingly congested airspace and operation. From Jan 2020, the U.S. Federal Aviation Administration (FAA) mandated the use of (ADS-B) as a key component of Next Gen project. LÄS MER

  4. 3. Generation and Detection of Adversarial Attacks in the Power Grid

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknik

    Författare :Oscar Larsson; [2022]
    Nyckelord :Machine Learning; Adversarial Learning; Power Systems; State Estimation; Detectability Constraints;

    Sammanfattning : Machine learning models are vulnerable to adversarial attacks that add perturbations to the input data. Here we model and simulate power flow in a power grid test case and generate adversarial attacks for these measurements in three different ways. LÄS MER

  5. 4. Generation and Detection of Adversarial Attacks for Reinforcement Learning Policies

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

    Författare :Axel Drotz; Markus Hector; [2021]
    Nyckelord :Deep Reinforcement Learning; Adversarial Attacks; Adversarial Attack Detection; Fast Gradient Sign Method; Deep Deterministic Policy Gradient; Deep Q-Learning; Likelihood Ratio Test; CUSUM;

    Sammanfattning : In this project we investigate the susceptibility ofreinforcement rearning (RL) algorithms to adversarial attacks.Adversarial attacks have been proven to be very effective atreducing performance of deep learning classifiers, and recently,have also been shown to reduce performance of RL agents. LÄS MER

  7. 5. On the Use of Model-Agnostic Interpretation Methods as Defense Against Adversarial Input Attacks on Tabular Data

    Uppsats för yrkesexamina på avancerad nivå, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Anton Kanerva; Fredrik Helgesson; [2020]
    Nyckelord :Machine learning; deep neural networks; model interpretation; cyber security; Maskininlärning; djupa neurala nätverk; modelltolkning; cybersäkerhet;

    Sammanfattning : Context. Machine learning is a constantly developing subfield within the artificial intelligence field. The number of domains in which we deploy machine learning models is constantly growing and the systems using these models spread almost unnoticeably in our daily lives through different devices. LÄS MER