Related papers: Protecting Privacy in Classifiers by Token Manipul…

We present a novel approach to lexical error recovery on textual input. An advanced robust tokenizer has been implemented that can not only correct spelling mistakes, but also recover from segmentation errors. Apart from the orthographic…

The remarkable success of machine learning has fostered a growing number of cloud-based intelligent services for mobile users. Such a service requires a user to send data, e.g. image, voice and video, to the provider, which presents a…

Non-malleable codes are randomized codes that protect coded messages against modification by functions in a tampering function class. These codes are motivated by providing tamper resilience in applications where a cryptographic secret is…

Short texts are omnipresent in real-time news, social network commentaries, etc. Traditional text representation methods have been successfully applied to self-contained documents of medium size. However, information in short texts is often…

Accurately learning from user data while providing quantifiable privacy guarantees provides an opportunity to build better ML models while maintaining user trust. This paper presents a formal approach to carrying out privacy preserving text…

In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization to safeguard…

In this study, we investigate the protection offered by federated learning algorithms against eavesdropping adversaries. In our model, the adversary is capable of intercepting model updates transmitted from clients to the server, enabling…

We find that the way we choose to represent data labels can have a profound effect on the quality of trained models. For example, training an image classifier to regress audio labels rather than traditional categorical probabilities…

The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural…

Language models typically tokenize raw text into sequences of subword identifiers from a predefined vocabulary, a process inherently sensitive to typographical errors, length variations, and largely oblivious to the internal structure of…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Tokenisation is the first step in almost all NLP tasks, and state-of-the-art transformer-based language models all use subword tokenisation algorithms to process input text. Existing algorithms have problems, often producing tokenisations…

Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…

Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens…

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be…

Token representations influence the efficiency and adaptability of language models, yet conventional tokenization strategies impose rigid segmentation boundaries that do not adjust dynamically to evolving contextual relationships. The…

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…