10 papers
Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its Derivatives
Kuanrong Liu, Siyuan Liang, Cheng Qian +2
As a general-purpose vision-language pretraining model, CLIP demonstrates strong generalization ability in image-text alignment tasks and has been widely adopted in downstream appl…
Text Adversarial Attacks with Dynamic Outputs
Wenqiang Wang, Siyuan Liang, Xiao Yan +1
Text adversarial attack methods are typically designed for static scenarios with fixed numbers of output labels and a predefined label space, relying on extensive querying of the v…
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
Tianrui Lou, Xiaojun Jia, Siyuan Liang +4
Physical adversarial attack methods expose the vulnerabilities of deep neural networks and pose a significant threat to safety-critical scenarios such as autonomous driving. Camouf…
Physical Adversarial Camouflage through Gradient Calibration and Regularization
Jiawei Liang, Siyuan Liang, Jianjie Huang +3
The advancement of deep object detectors has greatly affected safety-critical fields like autonomous driving. However, physical adversarial camouflage poses a significant security…
SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents
Siyuan Liang, Tianmeng Fang, Zhe Liu +5
With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal t…
Robust Anti-Backdoor Instruction Tuning in LVLMs
Yuan Xun, Siyuan Liang, Xiaojun Jia +2
Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contami…