English
Related papers

Related papers: Salsa Fresca: Angular Embeddings and Pre-Training …

200 papers

Malware detection is a popular application of Machine Learning for Information Security (ML-Sec), in which an ML classifier is trained to predict whether a given file is malware or benignware. Parameters of this classifier are typically…

Cryptography and Security · Computer Science 2019-03-15 Ethan M. Rudd , Felipe N. Ducau , Cody Wild , Konstantin Berlin , Richard Harang

Large language models (LLMs) offer personalized responses based on user interactions, but this use case raises serious privacy concerns. Homomorphic encryption (HE) is a cryptographic protocol supporting arithmetic computations in encrypted…

Cryptography and Security · Computer Science 2025-02-24 Donghwan Rho , Taeseong Kim , Minje Park , Jung Woo Kim , Hyunsik Chae , Ernest K. Ryu , Jung Hee Cheon

With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the evasion attacks and the poisoning attacks attempt to utilize…

Cryptography and Security · Computer Science 2022-08-16 Zeyan Liu , Fengjun Li , Jingqiang Lin , Zhu Li , Bo Luo

Federated Learning (FL) emerged as a paradigm for conducting machine learning across broad and decentralized datasets, promising enhanced privacy by obviating the need for direct data sharing. However, recent studies show that attackers can…

Computation and Language · Computer Science 2024-11-28 Xueluan Gong , Yuji Wang , Shuaike Li , Mengyuan Sun , Songze Li , Qian Wang , Kwok-Yan Lam , Chen Chen

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

Machine Learning · Computer Science 2025-06-27 Fei Wang , Baochun Li

Reinforcement learning (RL) with limited samples is common in real-world applications. However, offline RL performance under this constraint is often suboptimal. We consider an alternative approach to dealing with limited samples by…

Machine Learning · Computer Science 2025-11-14 Outongyi Lv , Yewei Yuan , Nana Liu

Advanced Encryption Standard (AES) is a widely adopted cryptographic algorithm, yet its practical implementations remain susceptible to side-channel and fault injection attacks. In this work, we propose a comprehensive framework that…

Cryptography and Security · Computer Science 2025-07-08 Nishant Chinnasami , Rye Stahle-Smith , Rasha Karakchi

Machine Learning (ML) promises to enhance the efficacy of Android Malware Detection (AMD); however, ML models are vulnerable to realistic evasion attacks--crafting realizable Adversarial Examples (AEs) that satisfy Android malware domain…

Machine Learning · Computer Science 2024-12-25 Hamid Bostani , Zhengyu Zhao , Zhuoran Liu , Veelasha Moonsamy

Homomorphic encryption (HE) is a promising privacy-preserving technique for cross-silo federated learning (FL), where organizations perform collaborative model training on decentralized data. Despite the strong privacy guarantee, general HE…

Cryptography and Security · Computer Science 2021-09-30 Zhifeng Jiang , Wei Wang , Yang Liu

Large Language Models (LLMs) exhibit significant safety disparities across languages, with low-resource languages (LRLs) often bypassing safety guardrails established for high-resource languages (HRLs) like English. Existing solutions, such…

Machine Learning · Computer Science 2026-02-27 Jiaming Liang , Zhaoxin Wang , Handing Wang

We present a quantum augmented variant of the dual lattice attack on the Learning with Errors (LWE) problem, using classical memory with quantum random access (QRACM). Applying our results to lattice parameters from the literature, we find…

Quantum Physics · Physics 2023-01-06 Martin R. Albrecht , Yixin Shen

Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of…

Computation and Language · Computer Science 2024-09-04 Myung Gyo Oh , Hong Eun Ahn , Leo Hyun Park , Taekyoung Kwon

Logistic Regression (LR) is the most widely used machine learning model in industry for its efficiency, robustness, and interpretability. Due to the problem of data isolation and the requirement of high model performance, many applications…

Cryptography and Security · Computer Science 2021-06-01 Chaochao Chen , Jun Zhou , Li Wang , Xibin Wu , Wenjing Fang , Jin Tan , Lei Wang , Alex X. Liu , Hao Wang , Cheng Hong

Malware detection have used machine learning to detect malware in programs. These applications take in raw or processed binary data to neural network models to classify as benign or malicious files. Even though this approach has proven…

Cryptography and Security · Computer Science 2020-04-20 Xiruo Wang , Risto Miikkulainen

The Learning With Errors ($\mathsf{LWE}$) problem asks to find $\mathbf{s}$ from an input of the form $(\mathbf{A}, \mathbf{b} = \mathbf{A}\mathbf{s}+\mathbf{e}) \in (\mathbb{Z}/q\mathbb{Z})^{m \times n} \times…

Cryptography and Security · Computer Science 2024-05-15 Thomas Debris-Alazard , Pouria Fallahpour , Damien Stehlé

Machine learning models and libraries can train datasets of different sizes and perform prediction and classification operations, but machine learning models and libraries cause slow and long training times on large datasets. This article…

Machine Learning · Computer Science 2025-09-17 Halil Hüseyin Çalışkan , Talha Koruk

Pretrained language models (LMs) are prone to arithmetic errors. Existing work showed limited success in probing numeric values from models' representations, indicating that these errors can be attributed to the inherent unreliability of…

Computation and Language · Computer Science 2025-10-27 Marek Kadlčík , Michal Štefánik , Timothee Mickus , Michal Spiegel , Josef Kuchař

Manifold learning (ML) aims to seek low-dimensional embedding from high-dimensional data. The problem is challenging on real-world datasets, especially with under-sampling data, and we find that previous methods perform poorly in this case.…

Machine Learning · Computer Science 2022-07-27 Zelin Zang , Siyuan Li , Di Wu , Ge Wang , Lei Shang , Baigui Sun , Hao Li , Stan Z. Li

Cross-lingual word embeddings (CLWE) are often evaluated on bilingual lexicon induction (BLI). Recent CLWE methods use linear projections, which underfit the training dictionary, to generalize on BLI. However, underfitting can hinder…

Computation and Language · Computer Science 2020-05-04 Mozhi Zhang , Yoshinari Fujinuma , Michael J. Paul , Jordan Boyd-Graber

The Learning with Errors problem (LWE) is one of the main candidates for post-quantum cryptography. At Asiacrypt 2017, coded-BKW with sieving, an algorithm combining the Blum-Kalai-Wasserman algorithm (BKW) with lattice sieving techniques,…

Cryptography and Security · Computer Science 2019-05-20 Erik Mårtensson
‹ Prev 1 3 4 5 6 7 10 Next ›