يعرض 1 - 8 نتائج من 8 نتيجة بحث عن '(( arts based defense ) OR ( ai large decrease ))', وقت الاستعلام: 0.09s تنقيح النتائج
  1. 1

    Towards secure private and trustworthy human-centric embedded machine learning: An emotion-aware facial recognition case study حسب Muhammad Atif Butt (10849980)

    منشور في 2023
    "…We find that input quantization partially degrades the efficacy of adversarial and backdoor attacks at the cost of a slight decrease in accuracy over clean inputs. By analyzing the explanations generated by SHAP, we identify that the decision of a FER model is largely influenced by features such as eyes, alar crease, lips, and jaws. …"
  2. 2

    Isolation and study of Lipase activity of an olive oil degrading Thermoactionomyces SP. (c2002) حسب Al Khudary, Rami

    منشور في 2002
    "…A ftlamentous, Gram-Positive, spore forming filamentous bacterium was isolated from soil (AI Koura - Lebanon) on rhodamine agar plates at 60°C. …"
    احصل على النص الكامل
    احصل على النص الكامل
    masterThesis
  3. 3

    Audio-deepfake detection: Adversarial attacks and countermeasures حسب Mouna Rabhi (17086969)

    منشور في 2024
    "…In particular, under graybox attack scenarios, we demonstrate that when starting from random noise, we can reduce the accuracy of the state-of-the-art detector from 98.5% to only 0.08%. To mitigate the effect of adversarial attacks on audio-deepfake detectors, we propose a highly generalizable, lightweight, simple, and effective add-on defense mechanism that can be implemented in any audio-deepfake detector. …"
  4. 4
  5. 5
  6. 6
  7. 7
  8. 8