Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attackby Tiansheng Huang, Sihao Hu,…
Approximating Optimal Morphing Attacks using Template Inversionby Laurent Colbois, Hatef Otroshi Shahreza, Sébastien MarcelFirst submitted…
Tropical Decision Boundaries for Neural Networks Are Robust Against Adversarial Attacksby Kurt Pasque, Christopher Teska,…
Convergence analysis of t-SNE as a gradient flow for point cloud on a manifoldby Seonghyeon…
SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Alteringby Xiaopeng Li,…
Superiority of Multi-Head Attention in In-Context Linear Regressionby Yingqian Cui, Jie Ren, Pengfei He, Jiliang…
Deep Embedding Clustering Driven by Sample Stabilityby Zhanwen Cheng, Feijiang Li, Jieting Wang, Yuhua QianFirst…
DGNN: Decoupled Graph Neural Networks with Structural Consistency between Attribute and Graph Embedding Representationsby Jinlu…
SliceGPT: Compress Large Language Models by Deleting Rows and Columnsby Saleh Ashkboos, Maximilian L. Croci,…
Embedding Attack Project (Work Report)by Jiameng Pu, Zafar TakhirovFirst submitted to arxiv on: 24 Jan…