Related papers: Visual Memory Injection Attacks for Multi-Turn Con…
Instruction-tuned Large Language Models (LLMs) have become a ubiquitous platform for open-ended applications due to their ability to modulate responses based on human instructions. The widespread use of LLMs holds significant potential for…
Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this…
Large vision-language models (LVLMs) have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information.…
Vision Large Language Models (VLLMs) represent a significant advancement in artificial intelligence by integrating image-processing capabilities with textual understanding, thereby enhancing user interactions and expanding application…
Large Language Models (LLMs) are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of…
Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…
The widespread application of large vision language models has significantly raised safety concerns. In this project, we investigate text prompt injection, a simple yet effective method to mislead these models. We developed an algorithm for…
Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal…
Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models,…
The rapid advancement of conversational agents, particularly chatbots powered by Large Language Models (LLMs), poses a significant risk of social engineering (SE) attacks on social media platforms. SE detection in multi-turn, chat-based…
Compared with Large Language Models (LLMs), Large Vision-Language Models (LVLMs) can also accept images as input, thus showcasing more interesting emergent capabilities and demonstrating impressive performance on various vision-language…
Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the adversarial…
Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…
The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…
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…
Deploying large vision-language models (LVLMs) introduces a unique vulnerability: susceptibility to malicious attacks via visual inputs. However, existing defense methods suffer from two key limitations: (1) They solely focus on textual…
Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…
Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack technique that…
The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…
Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While existing research has primarily focused on…