相关论文: REFORGE: Multi-modal Attacks Reveal Vulnerable Con…

The recent rapid growth of visual generative models trained on vast web-scale datasets has created significant tension with data privacy regulations and copyright laws, such as GDPR's ``Right to be Forgotten.'' This necessitates machine…

Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such distribution shifts are often brittle and degrade performance…

Understanding the capabilities of text-to-image (T2I) models in harmful content generation is essential to safety and compliance. However, human red-teaming is costly and inconsistent, driving the need for automatic tools that simulate…

Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such attacks is critical in order to ensure the safety and robustness of critical AI…

Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by…

The advent of multimodal deep learning models, such as CLIP, has unlocked new frontiers in a wide range of applications, from image-text understanding to classification tasks. However, these models are not safe for adversarial attacks,…

While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form of small, carefully chosen perturbations of their input,…

With the growing adoption of retrieval-augmented generation (RAG) systems, various attack methods have been proposed to degrade their performance. However, most existing approaches rely on unrealistic assumptions in which external attackers…

Recently, unified multimodal models (UMMs) have made remarkable progress in integrating visual understanding and generation, demonstrating strong potential for complex text-to-image (T2I) tasks. Despite their theoretical promise, a…

In this survey, we investigate the most recent techniques of resilient federated learning (ResFL) in CyberEdge networks, focusing on joint training with agglomerative deduction and feature-oriented security mechanisms. We explore adaptive…

Multimodal retrieval-augmented generation (RAG) enhances the visual reasoning capability of vision-language models (VLMs) by dynamically accessing information from external knowledge bases. In this work, we introduce \textit{Poisoned-MRAG},…

Unified Multimodal Models (UMMs) have shown impressive performance in both understanding and generation with a single architecture. However, UMMs still exhibit a fundamental inconsistency: understanding favors compact embeddings, whereas…

As digital medical imaging becomes more prevalent and archives increase in size, representation learning exposes an interesting opportunity for enhanced medical decision support systems. On the other hand, medical imaging data is often…

Multimodal Generative Models (MGMs) have rapidly evolved beyond text generation, now spanning diverse output modalities including images, music, video, human motion, and 3D objects, by integrating language with other sensory modalities…

Unsupervised Multiplex Graph Learning (UMGL) aims to learn node representations on various edge types without manual labeling. However, existing research overlooks a key factor: the reliability of the graph structure. Real-world data often…

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…

Adversarial Examples (AEs) generated by perturbing original training examples are useful in improving the robustness of Deep Learning (DL) based models. Most prior works, generate AEs that are either unconscionable due to lexical errors or…

Retrieval-augmented generation (RAG) is a widely adopted paradigm for enhancing LLMs in medical applications by incorporating expert multimodal knowledge during generation. However, the underlying retrieval databases may naturally contain,…

Concept erasure aims to selectively unlearning undesirable content in diffusion models (DMs) to reduce the risk of sensitive content generation. As a novel paradigm in concept erasure, most existing methods employ adversarial training to…

Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While recent studies have demonstrated the potential of such attacks, they typically rely on…