相关论文: Adversarial Attacks to Multi-Modal Models

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…

The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to…

Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single…

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…

In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…

Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks. To address this challenge, we first show iteratively generated…

In this paper, we propose to make a systematic study on machines multisensory perception under attacks. We use the audio-visual event recognition task against multimodal adversarial attacks as a proxy to investigate the robustness of…

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,…

Machine learning models have been shown vulnerable to adversarial attacks launched by adversarial examples which are carefully crafted by attacker to defeat classifiers. Deep learning models cannot escape the attack either. Most of…

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…

Cross-modal retrieval has become popular in recent years, particularly with the rise of multimedia. Generally, the information from each modality exhibits distinct representations and semantic information, which makes feature tends to be in…

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…

Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer from limited…

Face manipulation methods can be misused to affect an individual's privacy or to spread disinformation. To this end, we introduce a novel data-driven approach that produces image-specific perturbations which are embedded in the original…

Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time…

Adversarial ranking attacks have gained increasing attention due to their success in probing vulnerabilities, and, hence, enhancing the robustness, of neural ranking models. Conventional attack methods employ perturbations at a single…

Multi-targeted adversarial attacks aim to mislead classifiers toward specific target classes using a single perturbation generator with a conditional input specifying the desired target class. Existing methods face two key limitations: (1)…

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity…