Related papers: ATAAT: Adaptive Threat-Aware Adversarial Tuning Fr…
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…
Vision-language pre-training (VLP) models are vulnerable to adversarial examples, particularly in black-box scenarios. Existing multimodal attacks often suffer from limited perturbation diversity and unstable multi-stage pipelines. To…
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…
Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalizability across diverse downstream tasks. However, recent studies have revealed that VLMs, including CLIP, are highly vulnerable to adversarial…
With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to unimodal domains but have expanded to more complex multimodal…
Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical…
Vision-Language-Action (VLA) models map multimodal perception and language instructions to executable robot actions, making them particularly vulnerable to behavioral backdoor manipulation: a hidden trigger introduced during training can…
Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…
Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques…
Visual language modeling for automated driving is emerging as a promising research direction with substantial improvements in multimodal reasoning capabilities. Despite its advanced reasoning abilities, VLM-AD remains vulnerable to serious…
Vision-Language Models (VLMs), such as CLIP, have achieved impressive zero-shot recognition performance but remain highly susceptible to adversarial perturbations, posing significant risks in safety-critical scenarios. Previous…
Multimodal contrastive learning models (e.g., CLIP) can learn high-quality representations from large-scale image-text datasets, while they exhibit significant vulnerabilities to backdoor attacks, raising serious safety concerns. In this…
Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In-context learning is the ability of LMs to perform multiple…
Adversarial training enhances the robustness of Machine Learning (ML) models against adversarial attacks. However, obtaining labeled training and adversarial training data in network/cybersecurity domains is challenging and costly.…
As the key technology of augmented reality (AR), 3D recognition and tracking are always vulnerable to adversarial examples, which will cause serious security risks to AR systems. Adversarial examples are beneficial to improve the robustness…
Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks.…
Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular importance. An appropriate solution to adversarial attacks is…
Vision-Language-Action (VLA) models have achieved revolutionary progress in robot learning, enabling robots to execute complex physical robot tasks from natural language instructions. Despite this progress, their adversarial robustness…
Recent studies demonstrated the vulnerability of control policies learned through deep reinforcement learning against adversarial attacks, raising concerns about the application of such models to risk-sensitive tasks such as autonomous…
Deep learning has emerged as a leading approach for Automatic Modulation Classification (AMC), demonstrating superior performance over traditional methods. However, vulnerability to adversarial attacks and susceptibility to data…