Related papers: Targeted Attack on GPT-Neo for the SATML Language …

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…

Current text generation models are trained using real data which can potentially contain sensitive information, such as confidential patient information and the like. Under certain conditions output of the training data which they have…

Adversarial attacks against language models(LMs) are a significant concern. In particular, adversarial samples exploit the model's sensitivity to small input changes. While these changes appear insignificant on the semantics of the input…

Fine-tuning large language models (LLMs) on sensitive datasets raises privacy concerns, as training data extraction (TDE) attacks can expose highly confidential information. Existing defenses against such attacks either lack formal privacy…

Data augmentation is a widely employed technique to alleviate the problem of data scarcity. In this work, we propose a prompting-based approach to generate labelled training data for intent classification with off-the-shelf language models…

Language model pretraining generally targets a broad range of use cases and incorporates data from diverse sources. However, there are instances where we desire a model that excels in specific areas without markedly compromising performance…

The training process of large language models (LLMs) often involves varying degrees of test data contamination. Although current LLMs are achieving increasingly better performance on various benchmarks, their performance in practical…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…

Backdoor attacks pose a significant threat to the integrity of text classification models used in natural language processing. While several dirty-label attacks that achieve high attack success rates (ASR) have been proposed, clean-label…

Retrieval-Augmented Generation (RAG) offers a solution to mitigate hallucinations in Large Language Models (LLMs) by grounding their outputs to knowledge retrieved from external sources. The use of private resources and data in constructing…

Model extraction attacks (MEAs) on large language models (LLMs) have received increasing attention in recent research. However, existing attack methods typically adapt the extraction strategies originally developed for deep neural networks…

Previous learning-based vulnerability detection methods relied on either medium-sized pre-trained models or smaller neural networks from scratch. Recent advancements in Large Pre-Trained Language Models (LLMs) have showcased remarkable…

Advanced Persistent Threats (APTs) are prolonged, stealthy intrusions by skilled adversaries that compromise high-value systems to steal data or disrupt operations. Reconstructing complete attack chains from massive, heterogeneous logs is…

Graph Neural Networks (GNNs) are recognized as potent tools for processing real-world data organized in graph structures. Especially inductive GNNs, which allow for the processing of graph-structured data without relying on predefined graph…

Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract…

Recent work has designed methods to demonstrate that model updates in ASR training can leak potentially sensitive attributes of the utterances used in computing the updates. In this work, we design the first method to demonstrate…

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the…

Neural Machine Translation (NMT) models have been shown to be vulnerable to adversarial attacks, wherein carefully crafted perturbations of the input can mislead the target model. In this paper, we introduce ACT, a novel adversarial attack…

Hate speech is one of the main threats posed by the widespread use of social networks, despite efforts to limit it. Although attention has been devoted to this issue, the lack of datasets and case studies centered around scarcely…

High-quality training data has proven crucial for developing performant large language models (LLMs). However, commercial LLM providers disclose few, if any, details about the data used for training. This lack of transparency creates…