Related papers: UPTON: Preventing Authorship Leakage from Public T…
We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…
Authorship identification has proven unsettlingly effective in inferring the identity of the author of an unsigned document, even when sensitive personal information has been carefully omitted. In the digital era, individuals leave a…
Authorship obfuscation aims to disguise the identity of an author within a text by altering the writing style, vocabulary, syntax, and other linguistic features associated with the text author. This alteration needs to balance privacy and…
Data poisoning is a type of adversarial attack on training data where an attacker manipulates a fraction of data to degrade the performance of machine learning model. Therefore, applications that rely on external data-sources for training…
Backdoor data poisoning is a crucial technique for ownership protection and defending against malicious attacks. Embedding hidden triggers in training data can manipulate model outputs, enabling provenance verification, and deterring…
The problem of obfuscating the authorship of a text document has received little attention in the literature to date. Current approaches are ad-hoc and rely on assumptions about an adversary's auxiliary knowledge which makes it difficult to…
The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…
Data poisoning is a threat model in which a malicious actor tampers with training data to manipulate outcomes at inference time. A variety of defenses against this threat model have been proposed, but each suffers from at least one of the…
Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…
Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…
This paper investigates the critical issue of data poisoning attacks on AI models, a growing concern in the ever-evolving landscape of artificial intelligence and cybersecurity. As advanced technology systems become increasingly prevalent…
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…
Data poisoning is a training-time attack that undermines the trustworthiness of learned models. In a targeted data poisoning attack, an adversary manipulates the training dataset to alter the classification of a targeted test point. Given…
Machine learning models have achieved great success in supervised learning tasks for end-to-end training, which requires a large amount of labeled data that is not always feasible. Recently, many practitioners have shifted to…
As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy…
The prevalence of data scraping from social media as a means to obtain datasets has led to growing concerns regarding unauthorized use of data. Data poisoning attacks have been proposed as a bulwark against scraping, as they make data…
As AI writing support becomes ubiquitous, how disclosing its use affects reader perception remains a critical, underexplored question. We conducted a study with 261 participants to examine how revealing varying levels of AI involvement…
The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a…
Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…
Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small, concealed changes to the training data. In this work, we…