Related papers: VL-Trojan: Multimodal Instruction Backdoor Attacks…

Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject undetectable perturbations into the data during inference,…

Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase. In this work, we present AnyDoor, a test-time backdoor attack against multimodal…

Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive…

Instruction tuning enhances large vision-language models (LVLMs) but increases their vulnerability to backdoor attacks due to their open design. Unlike prior studies in static settings, this paper explores backdoor attacks in LVLM…

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…

Vision-Language Models (VLMs) have achieved remarkable success in tasks such as image captioning and visual question answering (VQA). However, as their applications become increasingly widespread, recent studies have revealed that VLMs are…

Multi-modal large language models (MLLMs) extend large language models (LLMs) to process multi-modal information, enabling them to generate responses to image-text inputs. MLLMs have been incorporated into diverse multi-modal applications,…

Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge.…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

Deep neural networks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The backdoor-compromised model will mis-classify to the target…

Vision-language models (VLMs) may memorize undesirable information from training data, motivating growing interest in machine unlearning. In this work, we present the first systematic survey and robustness analysis of VLM unlearning. We…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a…

Backdoor attacks have been shown to be a serious threat against deep learning systems such as biometric authentication and autonomous driving. An effective backdoor attack could enforce the model misbehave under certain predefined…

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use…

Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tasks. In this paper, we identify a novel security threat…

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…

Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…

The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite their growing…