10 accepted papers
Large vision-language models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal reasoning tasks. However, recent research shows that they are susceptible to adversarial examples. Existing LVLM attack methods are generally deployed in the white- or black-box setting, …
Existing audio adversarial attack methods suffer from poor transferability, primarily due to insufficient exploration of model decision mechanisms and overreliance on heuristic-driven algorithm design. This paper aims to alleviate this gap. Specifically, through observations across three mainstream
Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel Tutor-Student Reinforcement Learning (TSRL) framework to dynamically optimize the training curricul
Music deepfake detection is aimed at identifying whether songs are generated by AI. Current methods usually separate vocals from background music for detection, but this could leave residual forgery information in the background. Our study demonstrates for the first time that incorporating backgroun…
The development of voice cloning techniques has made forgery audios indistinguishable, posing an urgency to trace their sources. Many existing works focus on improving identification accuracy for audio deepfake algorithm recognition. However, most methods ignore the impact of complex information in…
Deep Hashing (DH)-based image retrieval has been widely applied to face-matching systems due to its accuracy and efficiency. However, this convenience comes with an increased risk of privacy leakage. DH models inherit the vulnerability to adversarial attacks, which can be used to prevent the retriev…
Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high ac…
In this paper, we consider the face swapping detection from the perspective of face identity. Face swapping aims to replace the target face with the source face and generate the fake face that the human cannot distinguish between real and fake. We argue that the fake face contains the explicit ident…
Adversarial example is a rising tool for voice privacy protection. By adding imperceptible noise to public audio, it prevents tampers from using zero-shot Voice Conversion (VC) to synthesize high quality speech with target speaker identity. However, many existing studies ignore the human perception…
With the rapid development of deepfake techniques, massive face manipulation videos appeared on social networks. These deepfake videos not only violated the original video of the author’s privacy, but also seriously threatened the security of the video database. Robust video hashing can map videos w…