Related papers: Vera Verto: Multimodal Hijacking Attack

Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabilities. However, the security issues associated with these models are becoming increasingly…

Large Language Models (LLMs) remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a feedback-driven Simulator for iterative query refinement;…

Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibility of hijacking…

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Machine learning (ML) techniques are increasingly common in security applications, such as malware and intrusion detection. However, ML models are often susceptible to evasion attacks, in which an adversary makes changes to the input (such…

As machine learning (ML) techniques are being increasingly used in many applications, their vulnerability to adversarial attacks becomes well-known. Test time attacks, usually launched by adding adversarial noise to test instances, have…

This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries. A maximum likelihood-based algorithm is proposed to find an…

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…

Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models (LLMs). However, how MLLMs process and utilize visual…

Current adversarial attacks for evaluating the robustness of vision-language pre-trained (VLP) models in multi-modal tasks suffer from limited transferability, where attacks crafted for a specific model often struggle to generalize…

Assistive embodied agents that can be instructed in natural language to perform tasks in open-world environments have the potential to significantly impact labor tasks like manufacturing or in-home care -- benefiting the lives of those who…

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol…

Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…

Vertical Federated Learning (VFL) enables an orchestrating active party to perform a machine learning task by cooperating with passive parties that provide additional task-related features for the same training data entities. While prior…

Federated Learning (FL) has been gaining popularity as a collaborative learning framework to train deep learning-based object detection models over a distributed population of clients. Despite its advantages, FL is vulnerable to model…

Vision-Language Models (VLMs) are rapidly replacing unimodal encoders in modern retrieval and recommendation systems. While their capabilities are well-documented, their robustness against adversarial manipulation in competitive ranking…

With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered. One such vulnerability makes itpossible for an adversary to obtain private information about the types of…

We explore visual prompt injection (VPI) that maliciously exploits the ability of large vision-language models (LVLMs) to follow instructions drawn onto the input image. We propose a new VPI method, "goal hijacking via visual prompt…