相关论文: Erased but Exploitable: Black-box Embedding-Aware …

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…

Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models, yet recent evidence shows that latent visual information often persists after unlearning. Existing adversarial approaches…

Multimodal Large Language Models (MLLMs) have achieved remarkable performance across vision-language tasks. Recent advancements allow these models to process multiple images as inputs. However, the vulnerabilities of multi-image MLLMs…

Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting,…

In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks predominantly focus on the visual modality, perturbing solely…

Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expose a critical yet underexplored vulnerability in the…

Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions…

Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…

Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation. Existing unlearning methods aim to make the process of…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…

Despite the remarkable generation capabilities of diffusion models, recent studies have shown that they can memorize and create harmful content when given specific text prompts. Although fine-tuning approaches have been developed to…

Extremely large image generators offer significant transformative potential across diverse sectors. It allows users to design specific prompts to generate realistic images through some black-box APIs. However, some studies reveal that image…

Recent research has shown Deep Neural Networks (DNNs) to be vulnerable to adversarial examples that induce desired misclassifications in the models. Such risks impede the application of machine learning in security-sensitive domains.…

Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…

Several years of research have shown that machine-learning systems are vulnerable to adversarial examples, both in theory and in practice. Until now, such attacks have primarily targeted visual models, exploiting the gap between human and…

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independently, in other cases,…

Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately…

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…