Jun Yan, Weiquan Huang, Qixian Zhang, Yan Bai, Shutai Zhang
Certified defenses that incorporate differential privacy have proven effective on Convolutional Neural Networks (CNNs), furnishing rigorous robustness guarantees against norm-bounded adversaries. However, the certified robustness behavior of Pixel Differential Privacy (PixelDP) remains largely unexplored with the self-attention architecture now dominating the deep-learning landscape. Given that the Transformer has a profound impact on our daily applications from the digital world to the physical world, it is crucial to study certified robustness through differential-privacy-style stability. To fill this research gap, we revisit this construction in Vision Transformers and identify a failure mode that is largely hidden in the convolutional setting. When noise is injected after the patch embedding, the Laplace mechanism with the inherited grouped $\ell_1$ sensitivity bound collapses to chance-level accuracy across noise scales, whereas the Gaussian mechanism remains trainable. This contrast isolates the source of failure: not the injected noise itself, but the geometry of the sensitivity constraint. We show that the attenuation induced by the inherited $Δ_{1,1}$ projection increases with layer width and kernel size according to a random-matrix scale $C/(\sqrt{M}+\sqrt{N})$. Replacing the $\ell_1$-type constraint with a spectral-norm constraint eliminates the collapse across datasets and architectures, but creates a fundamental obstacle: the repaired models no longer satisfy the sensitivity condition required by the standard Laplace certificate. We resolve this mismatch by deriving a dimension-free $(\varepsilon,\ δ)$-privacy guarantee for the Laplace mechanism under $\ell_2$ sensitivity through concentration of the privacy loss.
Jinhu Fu, Yan Bai, Yihang Lou, Li Sun, Jiahong Wu, Xiangxiang Chu, Sen Su
Knowledge editing aims to update outdated or incorrect knowledge in large language models without full retraining. Existing parameter-editing methods remain limited for long-sequence knowledge: single-point editors provide insufficient coverage for extended targets, while fixed chunk-based editors distribute editing effort uniformly across rigid predefined windows, failing to prioritize difficult, information-dense tokens. In this work, we show that token entropy is closely associated with both editing difficulty and semantic importance: high-entropy regions are harder to edit and often contain key factual content. Motivated by this observation, we propose DynEdit, a dynamic framework for long-sequence knowledge editing. DynEdit uses token-level entropy to guide non-uniform sliding, increasing the coverage of difficult high-entropy regions, and further applies entropy-guided token-level optimization to strengthen updates on information-dense tokens within each editing window. Experiments on three benchmarks and two backbone models show that DynEdit consistently outperforms competitive baselines across diverse long-form editing settings, achieving gains of up to +14.0 BLEU points on challenging paraphrase queries and near-saturated semantic scores on several diverse knowledge domains.
Jinhu Fu, Yan Bai Peking University, Tsinghua University, Longzhu He Beijing University of Posts and Telecommunications, Yihang Lou Huawei Technologies Ltd., Yanxiao Zhao, Li Sun Beijing University of Post and Telecommunications, Sen Su Beijing University of Posts and Telecommunications
Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring that the model can use it effectively to solve practical problems. (II) Narrow scope: Current methods focus primarily on structured fact triples, overlooking the diverse unstructured forms of factual information (e.g., news, articles) prevalent in real-world contexts. To address these challenges, we propose a new paradigm: teaching LLMs to edit knowledge via Chain of Thoughts (CoTs) reasoning (CoT2Edit). We first leverage language model agents for both structured and unstructured edited data to generate CoTs, building high-quality instruction data. The model is then trained to reason over edited knowledge through supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO). At inference time, we integrate Retrieval-Augmented Generation (RAG) to dynamically retrieve relevant edited facts for real-time knowledge editing. Experimental results demonstrate that our method achieves strong generalization across six diverse knowledge editing scenarios with just a single round of training on three open-source language models.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表