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