相关论文: PETGEN: Personalized Text Generation Attack on Dee…

Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image…

Counterspeech can be an effective method for battling hateful content on social media. Automated counterspeech generation can aid in this process. Generated counterspeech, however, can be viable only when grounded in the context of topic,…

Diffusion models (DMs) have revolutionized data generation, particularly in text-to-image (T2I) synthesis. However, the widespread use of personalized generative models raises significant concerns regarding privacy violations and copyright…

Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts. To…

Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…

Production machine learning systems are consistently under attack by adversarial actors. Various deep learning models must be capable of accurately detecting fake or adversarial input while maintaining speed. In this work, we propose one…

Data poisoning attacks manipulate training data to introduce unexpected behaviors into machine learning models at training time. For text-to-image generative models with massive training datasets, current understanding of poisoning attacks…

In the realm of IoT/CPS systems connected over mobile networks, traditional intrusion detection methods analyze network traffic across multiple devices using anomaly detection techniques to flag potential security threats. However, these…

Recommender systems play an important role in modern information and e-commerce applications. While increasing research is dedicated to improving the relevance and diversity of the recommendations, the potential risks of state-of-the-art…

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised…

Recommender systems play a crucial role in helping users to find their interested information in various web services such as Amazon, YouTube, and Google News. Various recommender systems, ranging from neighborhood-based,…

Adversarial classification is the task of performing robust classification in the presence of a strategic attacker. Originating from information hiding and multimedia forensics, adversarial classification recently received a lot of…

In this paper, we present an effective method to craft text adversarial samples, revealing one important yet underestimated fact that DNN-based text classifiers are also prone to adversarial sample attack. Specifically, confronted with…

Adversarial perturbations can be added to images to protect their content from unwanted inferences. These perturbations may, however, be ineffective against classifiers that were not {seen} during the generation of the perturbation, or…

Personalized text generation aims to infer users' writing style preferences from their historical texts and generate outputs that faithfully reflect these stylistic characteristics. Existing solutions primarily adopt two paradigms:…

Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically…

Social networks have become an indispensable part of our lives, with billions of people producing ever-increasing amounts of text. At such scales, content policies and their enforcement become paramount. To automate moderation, questionable…

Recent works show that text-to-image generative models are surprisingly vulnerable to a variety of poisoning attacks. Empirical results find that these models can be corrupted by altering associations between individual text prompts and…

Text-to-image diffusion models have been demonstrated with undesired generation due to unfiltered large-scale training data, such as sexual images and copyrights, necessitating the erasure of undesired concepts. Most existing methods focus…

Large language models (LLMs) have exhibited remarkable versatility and adaptability, while their widespread adoption across various applications also raises critical safety concerns. This paper focuses on the impact of backdoored LLMs.…