paper-with-me

홈 › Papers

Defensive Generation

2026-02-24 · Gabriele Farina, Juan Carlos Perdomo arxiv

We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of the observed data and a pre-specified collection of computational tests. Our contributions are twofold. First, we expand on connections between online high-dimensional multicalibration with respect to an RKHS and recent advances in expected variational inequality problems, enabling efficient algorithms for the former. We then apply this algorithmic machinery to the problem of outcome indistinguishability. Our procedure, Defensive Generation, is the first to efficiently produce online outcome indistinguishable generative models of non-Bernoulli outcomes that are unfalsifiable with respect to infinite classes of tests, including those that examine higher-order moments of the generated distributions. Furthermore, our method runs in near-linear time in the number of samples and achieves the optimal, vanishing T^{-1/2} rate for generation error.

📄 PDF Abstract BibTeX arXiv:2602.21390

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation

2024-12-18 · Minkyoung Kim, Yunha Kim, Hyeram Seo, Heejung Choi 외

Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to ha…

TruthfulQA

Defensive Patches for Robust Recognition in the Physical World

2022-04-13 · CVPR 2022 1 · Jiakai Wang, Zixin Yin, Pengfei Hu, Aishan Liu 외

To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which improves robustness by operations on input da…

Taming the Fragility of KV Cache Eviction in LLM Inference

2025-10-15 · Yuan Feng, Haoyu Guo, JunLin Lv, S. Kevin Zhou 외 arxiv

Large language models have revolutionized natural language processing, yet their deployment remains hampered by the substantial memory and runtime overhead of the transformer's Key-Value cache. To mitigate this, recent m…

Enhanced Attacks on Defensively Distilled Deep Neural Networks

2017-11-16 · Yujia Liu, Weiming Zhang, Shaohua Li, Nenghai Yu

Deep neural networks (DNNs) have achieved tremendous success in many tasks of machine learning, such as the image classification. Unfortunately, researchers have shown that DNNs are easily attacked by adversarial example…

Face RecognitionGeneral Classificationimage-classificationImage Classification+1

Automatic Generation of Ice Hockey Defensive Motion via Coverage Control and Control Barrier Functions

2021-11-21 · Kornvik Tanpipat, Takeshi Hatanaka, Masatoshi Hiroura

A successful defensive strategy in ice hockey games is often designed empirically by an experienced professional. The majority of previous work on automating the strategy focuses on analyzing spatial data to decide the m…

valid