6 papers
DICE: Disentangling Artist Style from Content via Contrastive Subspace Decomposition in Diffusion Models
Tong Zhang, Ru Zhang, Jianyi Liu
The recent proliferation of diffusion models has made style mimicry effortless, enabling users to imitate unique artistic styles without authorization. In deployed platforms, this…
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
Yihao Wang, Pengxiang Ding, Lingxiao Li +13
Vision-Language-Action (VLA) models typically bridge the gap between perceptual and action spaces by pre-training a large-scale Vision-Language Model (VLM) on robotic data. While t…
CLIProv: A Contrastive Log-to-Intelligence Multimodal Approach for Threat Detection and Provenance Analysis
Jingwen Li, Ru Zhang, Jianyi Liu +1
With the increasing complexity of cyberattacks, the proactive and forward-looking nature of threat intelligence has become more crucial for threat detection and provenance analysis…
Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel
Yihao Wang, Ruiqi Song, Lingxiao Li +2
Existing linguistic steganography schemes often overlook the conditional probability (CP) of tokens in the candidate pool, allocating the one coding to all tokens, which results in…
Toward Copyright Integrity and Verifiability via Multi-Bit Watermarking for Intelligent Transportation Systems
Yihao Wang, Lingxiao Li, Yifan Tang +2
Intelligent transportation systems (ITS) use advanced technologies such as artificial intelligence to significantly improve traffic flow management efficiency, and promote the inte…
U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario
Jiaxin Song, Xinyu Wang, Yihao Wang +4
With the widespread use of social media, user-generated content has surged on online platforms. When such content includes hateful, abusive, offensive, or cyberbullying behavior, i…