Related papers: Avengers Ensemble! Improving Transferability of Au…

Authorship attribution aims to identify the author of a text based on the stylometric analysis. Authorship obfuscation, on the other hand, aims to protect against authorship attribution by modifying a text's style. In this paper, we…

Recent advances in natural language processing have enabled powerful privacy-invasive authorship attribution. To counter authorship attribution, researchers have proposed a variety of rule-based and learning-based text obfuscation…

Authorship Attribution (AA) and Authorship Obfuscation (AO) are two competing tasks of increasing importance in privacy research. Modern AA leverages an author's consistent writing style to match a text to its author using an AA classifier.…

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…

The task of obfuscating writing style using sequence models has previously been investigated under the framework of obfuscation-by-transfer, where the input text is explicitly rewritten in another style. These approaches also often lead to…

The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. However, while LLMs…

Authorship obfuscation, rewriting a text to intentionally obscure the identity of the author, is an important but challenging task. Current methods using large language models (LLMs) lack interpretability and controllability, often ignoring…

We propose a new randomized ensemble technique with a provable security guarantee against black-box transfer attacks. Our proof constructs a new security problem for random binary classifiers which is easier to empirically verify and a…

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…

Authorship attribution is the problem of identifying the most plausible author of an anonymous text from a set of candidate authors. Researchers have investigated same-topic and cross-topic scenarios of authorship attribution, which differ…

Maintaining anonymity in natural language communication remains a challenging task. Even when the number of candidate authors is large, standard authorship attribution techniques that analyze writing style predict the original author with…

Protecting the anonymity of authors has become a difficult task given the rise of automated authorship attributors. These attributors are capable of attributing the author of a text amongst a pool of authors with great accuracy. In order to…

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…

Authorship attribution mainly deals with undecided authorship of literary texts. Authorship attribution is useful in resolving issues like uncertain authorship, recognize authorship of unknown texts, spot plagiarism so on. Statistical…

Source code segment authorship identification is the task of identifying the author of a source code segment through supervised learning. It has vast importance in plagiarism detection, digital forensics, and several other law enforcement…

Random subspace method has wide security applications such as providing certified defenses against adversarial and backdoor attacks, and building robustly aligned LLM against jailbreaking attacks. However, the explanation of random subspace…

We propose a new approach for the authorship attribution task that leverages the various linguistic representations learned at different layers of pre-trained transformer-based models. We evaluate our approach on three datasets, comparing…

Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, they also exhibit weak…

Forensic scientists often need to identify an unknown speaker or writer in cases such as ransom calls, covert recordings, alleged suicide notes, or anonymous online communications, among many others. Speaker recognition in the speech domain…

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…