TA2.L1.3
Special Session Paper
View Manuscript
EXPOSING THE LIMITS OF DEEPFAKE DETECTION USING NOVEL FACIAL MOLE ATTACK: A PERCEPTUAL BLACK-BOX ADVERSARIAL ATTACK STUDY
Qurat Ul Ain, Ali Javed, University of Engineering and Technology-Taxila, Pakistan, Pakistan; Khalid Mahmood Malik, University of Michigan, Flint, MI, USA, United States of America; Aun Irtaza, University of Engineering and Technology-Taxila, Pakistan, Pakistan
Session:
TA2.L1: Recent Advances in Multimedia Forensics in the AI-Generative Era Lecture
Track:
Special Sessions
Location:
Capital Suite - 10
Presentation Time:
Tue, 29 Oct, 11:06 - 11:24 Gulf Standard Time (UTC +4)
Session Co-Chairs:
Luca Guarnera, University of Catania, Italy and Alessandro Ortis, University of Catania, Italy
Session TA2.L1
Special Session Paper
TA2.L1.1: On the Exploitation of DCT-Traces in the Generative-AI Domain
Orazio Pontorno, Luca Guarnera, Sebastiano Battiato, University of Catania, Italy
Special Session Paper
TA2.L1.2: EXPLORING THE IMPACT OF MOIRE PATTERN ON DEEPFAKE DETECTORS
Razaib Tariq, Sungkyunkwan University, South Korea, Korea, Republic of; Shahroz Tariq, CSIRO's Data61 Australia,, Australia; Simon Woo, Sungkyunkwan University, South Korea, Korea, Republic of
Special Session Paper
TA2.L1.3: EXPOSING THE LIMITS OF DEEPFAKE DETECTION USING NOVEL FACIAL MOLE ATTACK: A PERCEPTUAL BLACK-BOX ADVERSARIAL ATTACK STUDY
Qurat Ul Ain, Ali Javed, University of Engineering and Technology-Taxila, Pakistan, Pakistan; Khalid Mahmood Malik, University of Michigan, Flint, MI, USA, United States of America; Aun Irtaza, University of Engineering and Technology-Taxila, Pakistan, Pakistan
TA2.L1.4: AI-GENERATED IMAGE DETECTION WITH WASSERSTEIN DISTANCE COMPRESSION AND DYNAMIC AGGREGATION
Zihang Lyu, Jun Xiao, Cong Zhang, Kin-Man Lam, The Hong Kong Polytechnic University, Hong Kong
TA2.L1.5: INCREASING TRUST IN IMAGE ANALYSIS BY DETECTING TRELLIS QUANTIZATION IN JPEG IMAGES
Nora Hofer, University of Innsbruck, Austria
Contacts