3 citations · 15 across the 21 of their papers we have counts for
13 papers · 1 filter
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…
RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation
Enguang Liu, Siyuan Liang, Liming Lu +4
The safety and reliability of embodied agents rely on accurate and unbiased visual perception. However, existing benchmarks mainly emphasize generalization and robustness under per…
Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation
Ruoyu Chen, Xiaoqing Guo, Kangwei Liu +6
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs. Yet, the extent to which generated token…
Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models
Jiawei Liang, Jianjie Huang, Xianghao Jiao +3
Multimodal large language models (MLLMs) have achieved strong vision-language performance, yet their token-level visual evidence remains difficult to inspect. Recent logit-lens att…
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…
No Query, No Access
Wenqiang Wang, Siyuan Liang, Yangshijie Zhang +3
Textual adversarial attacks mislead NLP models, including Large Language Models (LLMs), by subtly modifying text. While effective, existing attacks often require knowledge of the v…
T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models
Siyuan Liang, Jiayang Liu, Jiecheng Zhai +5
The rapid development of generative artificial intelligence has made text to video models essential for building future multimodal world simulators. However, these models remain vu…
Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
Xuan Wang, Siyuan Liang, Dongping Liao +6
Institutions with limited data and computing resources often outsource model training to third-party providers in a semi-honest setting, assuming adherence to prescribed training p…
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Haotian Luo, Li Shen, Haiying He +6
Recently, long-thought reasoning LLMs, such as OpenAI's O1, adopt extended reasoning processes similar to how humans ponder over complex problems. This reasoning paradigm significa…