Despite the remarkable performance of video-based large language models (LLMs), their adversarial threat remains unexplored. To fill this gap, we propose the first adversarial attack tailored for video-based LLMs by crafting flow-based multi-modal adversarial perturbations on a small fraction of frames within a video, dubbed FMM-Attack. Extensive experiments show that our attack can effectively induce video-based LLMs to generate incorrect answers when videos are added with imperceptible adversarial perturbations. Intriguingly, our FMM-Attack can also induce garbling in the model output, prompting video-based LLMs to hallucinate. Overall, our observations inspire a further understanding of multi-modal robustness and safety-related feature alignment across different modalities, which is of great importance for various large multi-modal models. Our code is available at https://github.com/THU-Kingmin/FMM-Attack.
Large vision-language models (VLMs) such as GPT-4 have achieved exceptional performance across various multi-modal tasks. However, the deployment of VLMs necessitates substantial energy consumption and computational resources. Once attackers maliciously induce high energy consumption and latency time (energy-latency cost) during inference of VLMs, it will exhaust computational resources. In this paper, we explore this attack surface about availability of VLMs and aim to induce high energy-latency cost during inference of VLMs. We find that high energy-latency cost during inference of VLMs can be manipulated by maximizing the length of generated sequences. To this end, we propose verbose images, with the goal of crafting an imperceptible perturbation to induce VLMs to generate long sentences during inference. Concretely, we design three loss objectives. First, a loss is proposed to delay the occurrence of end-of-sequence (EOS) token, where EOS token is a signal for VLMs to stop generating further tokens. Moreover, an uncertainty loss and a token diversity loss are proposed to increase the uncertainty over each generated token and the diversity among all tokens of the whole generated sequence, respectively, which can break output dependency at token-level and sequence-level. Furthermore, a temporal weight adjustment algorithm is proposed, which can effectively balance these losses. Extensive experiments demonstrate that our verbose images can increase the length of generated sequences by 7.87 times and 8.56 times compared to original images on MS-COCO and ImageNet datasets, which presents potential challenges for various applications. Our code is available at https://github.com/KuofengGao/Verbose_Images.
Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with a downstream-oriented backdoor. On downstream tasks, one victim model performs well on clean samples but predicts a specific target class whenever a specific trigger is present. For injecting a backdoor, existing attacks depend on a large amount of additional data to maliciously fine-tune the entire pre-trained CLIP model, which makes them inapplicable to data-limited scenarios. In this work, motivated by the recent success of learnable prompts, we address this problem by injecting a backdoor into the CLIP model in the prompt learning stage. Our method named BadCLIP is built on a novel and effective mechanism in backdoor attacks on CLIP, i.e., influencing both the image and text encoders with the trigger. It consists of a learnable trigger applied to images and a trigger-aware context generator, such that the trigger can change text features via trigger-aware prompts, resulting in a powerful and generalizable attack. Extensive experiments conducted on 11 datasets verify that the clean accuracy of BadCLIP is similar to those of advanced prompt learning methods and the attack success rate is higher than 99% in most cases. BadCLIP is also generalizable to unseen classes, and shows a strong generalization capability under cross-dataset and cross-domain settings.
Backdoor defenses have been studied to alleviate the threat of deep neural networks (DNNs) being backdoor attacked and thus maliciously altered. Since DNNs usually adopt some external training data from an untrusted third party, a robust backdoor defense strategy during the training stage is of importance. We argue that the core of training-time defense is to select poisoned samples and to handle them properly. In this work, we summarize the training-time defenses from a unified framework as splitting the poisoned dataset into two data pools. Under our framework, we propose an adaptively splitting dataset-based defense (ASD). Concretely, we apply loss-guided split and meta-learning-inspired split to dynamically update two data pools. With the split clean data pool and polluted data pool, ASD successfully defends against backdoor attacks during training. Extensive experiments on multiple benchmark datasets and DNN models against six state-of-the-art backdoor attacks demonstrate the superiority of our ASD. Our code is available at https://github.com/KuofengGao/ASD.
With the thriving of deep learning in processing point cloud data, recent works show that backdoor attacks pose a severe security threat to 3D vision applications. The attacker injects the backdoor into the 3D model by poisoning a few training samples with trigger, such that the backdoored model performs well on clean samples but behaves maliciously when the trigger pattern appears. Existing attacks often insert some additional points into the point cloud as the trigger, or utilize a linear transformation (e.g., rotation) to construct the poisoned point cloud. However, the effects of these poisoned samples are likely to be weakened or even eliminated by some commonly used pre-processing techniques for 3D point cloud, e.g., outlier removal or rotation augmentation. In this paper, we propose a novel imperceptible and robust backdoor attack (IRBA) to tackle this challenge. We utilize a nonlinear and local transformation, called weighted local transformation (WLT), to construct poisoned samples with unique transformations. As there are several hyper-parameters and randomness in WLT, it is difficult to produce two similar transformations. Consequently, poisoned samples with unique transformations are likely to be resistant to aforementioned pre-processing techniques. Besides, as the controllability and smoothness of the distortion caused by a fixed WLT, the generated poisoned samples are also imperceptible to human inspection. Extensive experiments on three benchmark datasets and four models show that IRBA achieves 80%+ ASR in most cases even with pre-processing techniques, which is significantly higher than previous state-of-the-art attacks.
The security of deep neural networks (DNNs) has attracted increasing attention due to their widespread use in various applications. Recently, the deployed DNNs have been demonstrated to be vulnerable to Trojan attacks, which manipulate model parameters with bit flips to inject a hidden behavior and activate it by a specific trigger pattern. However, all existing Trojan attacks adopt noticeable patch-based triggers (e.g., a square pattern), making them perceptible to humans and easy to be spotted by machines. In this paper, we present a novel attack, namely hardly perceptible Trojan attack (HPT). HPT crafts hardly perceptible Trojan images by utilizing the additive noise and per pixel flow field to tweak the pixel values and positions of the original images, respectively. To achieve superior attack performance, we propose to jointly optimize bit flips, additive noise, and flow field. Since the weight bits of the DNNs are binary, this problem is very hard to be solved. We handle the binary constraint with equivalent replacement and provide an effective optimization algorithm. Extensive experiments on CIFAR-10, SVHN, and ImageNet datasets show that the proposed HPT can generate hardly perceptible Trojan images, while achieving comparable or better attack performance compared to the state-of-the-art methods. The code is available at: https://github.com/jiawangbai/HPT.
Deep hashing has become a popular method in large-scale image retrieval due to its computational and storage efficiency. However, recent works raise the security concerns of deep hashing. Although existing works focus on the vulnerability of deep hashing in terms of adversarial perturbations, we identify a more pressing threat, backdoor attack, when the attacker has access to the training data. A backdoored deep hashing model behaves normally on original query images, while returning the images with the target label when the trigger presents, which makes the attack hard to be detected. In this paper, we uncover this security concern by utilizing clean-label data poisoning. To the best of our knowledge, this is the first attempt at the backdoor attack against deep hashing models. To craft the poisoned images, we first generate the targeted adversarial patch as the backdoor trigger. Furthermore, we propose the confusing perturbations to disturb the hashing code learning, such that the hashing model can learn more about the trigger. The confusing perturbations are imperceptible and generated by dispersing the images with the target label in the Hamming space. We have conducted extensive experiments to verify the efficacy of our backdoor attack under various settings. For instance, it can achieve 63% targeted mean average precision on ImageNet under 48 bits code length with only 40 poisoned images.