Related papers: Enhancing Targeted Adversarial Attacks on Large Vi…

Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In this paper, we present IntentGuard, a general defense…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Recent years have witnessed remarkable advances in Large Vision-Language Models (LVLMs), which have achieved human-level performance across various complex vision-language tasks. Following LLaVA's paradigm, mainstream LVLMs typically employ…

We study adversarial robustness of open-source vision-language model (VLM) agents deployed in a self-contained e-commerce environment built to simulate realistic pre-deployment conditions. We evaluate two agents, LLaVA-v1.5-7B and…

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…

Vision-Large-Language-Models (Vision-LLMs) are increasingly being integrated into autonomous driving (AD) systems due to their advanced visual-language reasoning capabilities, targeting the perception, prediction, planning, and control…

Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure. Conversely,…

Despite the remarkable success of the LLaVA architecture for vision-language tasks, its design inherently struggles to effectively integrate visual features due to the inherent mismatch between text and vision modalities. We tackle this…

Large Language Model (LLM) agents are increasingly integrated into critical systems, leveraging external tools to interact with the real world. However, this capability exposes them to Indirect Prompt Injection (IPI), where attackers embed…

Large language models (LLMs) based on decoder-only transformers have demonstrated superior text understanding capabilities compared to CLIP and T5-series models. However, the paradigm for utilizing current advanced LLMs in text-to-image…

The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection attacks. In these attacks, malicious instructions embedded…

Black-box query attacks, which rely only on the output of the victim model, have proven to be effective in attacking deep learning models. However, existing black-box query attacks show low performance in a novel scenario where only a few…

Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle…

Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…

Large language models (LLMs) are increasingly deployed in real-world applications ranging from chatbots to agentic systems, where they are expected to process untrusted data and follow trusted instructions. Failure to distinguish between…

Long video understanding is a significant and ongoing challenge in the intersection of multimedia and artificial intelligence. Employing large language models (LLMs) for comprehending video becomes an emerging and promising method. However,…

Current black-box adversarial attacks either require multiple queries or diffusion models to produce adversarial samples that can impair the target model performance. However, these methods require training a surrogate loss or diffusion…

Recent progress in image generation models (IGMs) enables high-fidelity content creation but also amplifies risks, including the reproduction of copyrighted content and the generation of offensive content. Image Generation Model Unlearning…

Current large language models (LLMs) provide a strong foundation for large-scale user-oriented natural language tasks. A large number of users can easily inject adversarial text or instructions through the user interface, thus causing LLMs…

Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can leverage inherent weaknesses in the models, resulting in…