16 papers
Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning
Ao Zhou, Zhiwei Jiang, Zifeng Cheng +4
Uncertainty Quantification (UQ) aims to measure the reliability of model predictions, serving as a critical safeguard for deploying Vision-Language Models (VLMs) in safety-critical…
Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks
Shangze Li, Chuancheng Shi, Simiao Xie +6
With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward white-box attacks that directly…
ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation
Cong Wang, Haiyu Wu, Zhiwei Jiang +4
Concept erasure aims to prevent image generative models from producing unsafe content while preserving their general generative capability. Meanwhile, next-scale autoregressive (AR…
Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
Qiru Li, Ao Zhou, Zhiwei Jiang +4
Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurre…
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…
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…