7 papers
Pareto-Improving Adversarial Attacks with Primal-Dual Regularization
Yang Dai, Longfei Zhang, Wei Tao +3
Transferable adversarial attacks are arguably the most practical black-box threat model. Under the same perturbation budget, stronger transfer attacks attain higher attack success…
Look Clearly Before Answering: Mitigating Hallucinations in LVLMs via Saliency-Driven Perceptual Realignment
Pengxu Chen, Yao Zhu, Guangming Zhu +4
Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding. However, they remain prone to hallucinations, generating responses that…
Knowledge-guided Disentanglement with Atomic Actions for Action Recognition
Tianci Wu, Siqi Cao, Guangming Zhu +6
Action recognition in complex scenes often involves multiple concurrent fine-grained actions, making it challenging to model internal action structures. Most existing methods rely…
Sketch and Text Synergy: Fusing Structural Contours and Descriptive Attributes for Fine-Grained Image Retrieval
Siyuan Wang, Hanchen Gao, Guangming Zhu +5
Fine-grained image retrieval via hand-drawn sketches or textual descriptions remains a critical challenge due to inherent modality gaps. While hand-drawn sketches capture complex s…
The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers
Wei Tao, Yang Dai, Jincai Huang +1
Crafting adversarial examples can be formulated as an optimization problem. While sign-based optimizers such as I-FGSM and MI-FGSM have become the de facto standard for the induced…
TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models
Yang Dai, Oubo Ma, Longfei Zhang +6
Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks a…
Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
Yang Dai, Oubo Ma, Longfei Zhang +6
Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL). Yet, it poses challenges due to substant…