English
Related papers

Related papers: Subject-level Inference for Realistic Text Anonymi…

200 papers

Speech data conveys sensitive speaker attributes like identity or accent. With a small amount of found data, such attributes can be inferred and exploited for malicious purposes: voice cloning, spoofing, etc. Anonymization aims to make the…

Computation and Language · Computer Science 2020-02-14 Brij Mohan Lal Srivastava , Nathalie Vauquier , Md Sahidullah , Aurélien Bellet , Marc Tommasi , Emmanuel Vincent

Prediction-Powered Inference (PPI) is a recently proposed statistical inference technique for parameter estimation that leverages pseudo-labels on both labeled and unlabeled data to construct an unbiased, low-variance estimator. In this…

Machine Learning · Computer Science 2025-10-28 Noa Shoham , Ron Dorfman , Shalev Shaer , Kfir Y. Levy , Yaniv Romano

Speaker anonymization is an effective privacy protection solution that aims to conceal the speaker's identity while preserving the naturalness and distinctiveness of the original speech. Mainstream approaches use an utterance-level vector…

Audio and Speech Processing · Electrical Eng. & Systems 2024-05-20 Jixun Yao , Qing Wang , Pengcheng Guo , Ziqian Ning , Lei Xie

Zipf's law defines an inverse proportion between a word's ranking in a given corpus and its frequency in it, roughly dividing the vocabulary into frequent words and infrequent ones. Here, we stipulate that within a domain an author's…

Computation and Language · Computer Science 2022-02-24 Osnat Mokryn , Hagit Ben-Shoshan

The detection of Personally Identifiable Information (PII) is critical for privacy compliance but remains challenging in low-resource languages due to linguistic diversity and limited annotated data. We present RECAP, a hybrid framework…

Users posting online expect to remain anonymous unless they have logged in, which is often needed for them to be able to discuss freely on various topics. Preserving the anonymity of a text's writer can be also important in some other…

Computation and Language · Computer Science 2017-07-31 Georgi Karadjov , Tsvetomila Mihaylova , Yasen Kiprov , Georgi Georgiev , Ivan Koychev , Preslav Nakov

Membership inference attacks allow adversaries to determine whether a particular example was contained in the model's training dataset. While previous works have confirmed the feasibility of such attacks in various applications, none has…

Cryptography and Security · Computer Science 2023-11-28 Guangke Chen , Yedi Zhang , Fu Song

Understanding how software developers think, make decisions, and behave remains a key challenge in software engineering (SE). Verbalization techniques (methods that capture spoken or written thought processes) offer a lightweight and…

In the scenario of the Voice Privacy challenge, anonymization is achieved by converting all utterances from a source speaker to match the same target identity; this identity being randomly selected. In this context, an attacker with maximum…

Sound · Computer Science 2021-10-01 Pierre Champion , Denis Jouvet , Anthony Larcher

Spectral topic modeling algorithms operate on matrices/tensors of word co-occurrence statistics to learn topic-specific word distributions. This approach removes the dependence on the original documents and produces substantial gains in…

Computation and Language · Computer Science 2017-11-21 Moontae Lee , David Bindel , David Mimno

Authorship analysis (AA) is the study of unveiling the hidden properties of authors from a body of exponentially exploding textual data. It extracts an author's identity and sociolinguistic characteristics based on the reflected writing…

Computation and Language · Computer Science 2016-06-06 Steven H. H. Ding , Benjamin C. M. Fung , Farkhund Iqbal , William K. Cheung

Source Inference Attack (SIA) in Federated Learning (FL) aims to identify which client used a target data point for local model training. It allows the central server to audit clients' data usage. In cross-silo FL, a client (silo) collects…

Cryptography and Security · Computer Science 2024-10-01 Jiaxin Li , Marco Arazzi , Antonino Nocera , Mauro Conti

Speaker anonymization aims to protect the privacy of speakers while preserving spoken linguistic information from speech. Current mainstream neural network speaker anonymization systems are complicated, containing an F0 extractor, speaker…

Sound · Computer Science 2022-04-28 Xiaoxiao Miao , Xin Wang , Erica Cooper , Junichi Yamagishi , Natalia Tomashenko

With Internet users constantly leaving a trail of text, whether through blogs, emails, or social media posts, the ability to write and protest anonymously is being eroded because artificial intelligence, when given a sample of previous…

Machine Learning · Computer Science 2021-10-19 Rishi Balakrishnan , Stephen Sloan , Anil Aswani

Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence…

Computation and Language · Computer Science 2025-07-16 Anders Ledberg , Anna Thalén

In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on word embeddings lack transparency and interpretability. We…

Computation and Language · Computer Science 2023-07-19 Francisco Valentini , Germán Rosati , Damián Blasi , Diego Fernandez Slezak , Edgar Altszyler

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the…

Machine Learning · Statistics 2025-10-08 Eric Aubinais , Elisabeth Gassiat , Pablo Piantanida

Large language models (LLMs) have transformed natural language processing, but their ability to memorize training data poses significant privacy risks. This paper investigates model inversion attacks on the Llama 3.2 model, a multilingual…

Machine Learning · Computer Science 2025-07-08 Sathesh P. Sivashanmugam

When analyzing data researchers make some decisions that are either arbitrary, based on subjective beliefs about the data generating process, or for which equally justifiable alternative choices could have been made. This wide range of…

Documents revealing sensitive information about individuals must typically be de-identified. This de-identification is often done by masking all mentions of personally identifiable information (PII), thereby making it more difficult to…

Computation and Language · Computer Science 2025-05-20 Lucas Georges Gabriel Charpentier , Pierre Lison
‹ Prev 1 3 4 5 6 7 10 Next ›