6 papers
TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors
Xia Du, Zhuosen Bao, Zheng Lin +6
Recent diffusion models have achieved remarkable realism in facial image synthesis, posing growing challenges to artificial intelligence-generated content (AIGC) forensic detectors…
What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
Yusheng He, Jizhe Zhou, Xia Du +3
Hallucination remains one of the key challenges undermining the reliability of Large Vision-Language Models (LVLMs). But what makes an LVLM hallucinate less? Many existing efforts…
SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy
Zhuosen Bao, Xia Du, Zheng Lin +8
With the deep integration of facial recognition into online banking, identity verification, and other networked services, achieving effective decoupling of identity information fro…
IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection
Jiajie Zhu, Xia Du, Xiaoyuan Liu +4
The rapid advancements in artificial intelligence have significantly accelerated the adoption of speech recognition technology, leading to its widespread integration across various…
Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generation
Xia Du, Xiaoyuan Liu, Jizhe Zhou +7
Traditional CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) schemes are increasingly vulnerable to automated attacks powered by deep neural net…
DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection
Xia Du, Jiajie Zhu, Jizhe Zhou +5
In the field of digital security, Reversible Adversarial Examples (RAE) combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and…