collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors

Shichao Kan, Chengpeng Hong, Jingtong Dou +8

As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors a…

cs.CV2026

Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning

Chih-Ting Liao, Fei Shen, Xin Cao +1

The standard way to read latent knowledge out of a model, a linear probe confirmed by a steering recovery, can systematically overstate what a vision-language model (VLM) actually…

cs.CV2026

Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models

Shaotian Li, Shangze Li, Chuancheng Shi +5

Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) performance remain poorly unde…

cs.CV2026

Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities

Jingtong Dou, Chuancheng Shi, Jian Wang +3

As generative artificial intelligence evolves, deepfake attacks have escalated from single-modality manipulations to complex, multimodal threats. Existing forensic techniques face…

cs.CV2026

Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons

Xianhui Zhang, Chengyu Xie, Linxia Zhu +6

Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanis…

cs.CV2026

TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention

Chuancheng Shi, Shangze Li, Wenjun Lu +5

Despite their capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current defenses predominantly rely on the "locality hypothesis", suppres…