Open access
2026
A Novel Glow Adversarial Attack for Proactive Deepfake Defense
In-depth analyses of various advanced deepfake generation frameworks show that the proposed GlowAttack achieves improved visual quality while maintaining strong transferability at both the model and class levels, thereby exceeding existing adversarial proactive defences.
Maryam Bukhari, M. Maqsood, Miyoung Lee et al.
· IEEE Access · 0 citations