Related papers: UPTON: Preventing Authorship Leakage from Public T…
Knowledge distillation has become a cornerstone in modern machine learning systems, celebrated for its ability to transfer knowledge from a large, complex teacher model to a more efficient student model. Traditionally, this process is…
We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An adversary first adds a few carefully crafted points to the…
Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…
As in-the-wild data are increasingly involved in the training stage, machine learning applications become more susceptible to data poisoning attacks. Such attacks typically lead to test-time accuracy degradation or controlled misprediction.…
Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…
Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily…
Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and OpenAI leverages examples submitted in the browser…
Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also…
Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, causing models to…
Property inference attacks consider an adversary who has access to the trained model and tries to extract some global statistics of the training data. In this work, we study property inference in scenarios where the adversary can…
AI-based code generators have gained a fundamental role in assisting developers in writing software starting from natural language (NL). However, since these large language models are trained on massive volumes of data collected from…
The widespread adoption of generative models such as Stable Diffusion and ChatGPT has made them increasingly attractive targets for malicious exploitation, particularly through data poisoning. Existing poisoning attacks compromising…
Today, the publication of microdata poses a privacy threat. Vast research has striven to define the privacy condition that microdata should satisfy before it is released, and devise algorithms to anonymize the data so as to achieve this…
Within the current context of Information Societies, large amounts of information are daily exchanged and/or released. The sensitive nature of much of this information causes a serious privacy threat when documents are uncontrollably made…
Data poisoning is an adversarial scenario where an attacker feeds a specially crafted sequence of samples to an online model in order to subvert learning. We introduce Lethean Attack, a novel data poisoning technique that induces…
Deep learning (DL) models for natural language-to-code generation have become integral to modern software development pipelines. However, their heavy reliance on large amounts of data, often collected from unsanitized online sources,…
The unprecedented availability of training data fueled the rapid development of powerful neural networks in recent years. However, the need for such large amounts of data leads to potential threats such as poisoning attacks: adversarial…
Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…
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…
Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and facilitate flexible…