Related papers: Prompt-driven Transferable Adversarial Attack on P…

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…

Adversarial examples pose significant threats to deep neural networks (DNNs), and their property of transferability in the black-box setting has led to the emergence of transfer-based attacks, making it feasible to target real-world…

Achieving robust 3D perception in the face of corrupted data presents an challenging hurdle within 3D vision research. Contemporary transformer-based point cloud recognition models, albeit advanced, tend to overfit to specific patterns,…

Training state-of-the-art (SOTA) deep learning models requires a large amount of data. The visual information present in the training data can be misused, which creates a huge privacy concern. One of the prominent solutions for this issue…

State-of-the-art crowd counting and localization are primarily modeled using two paradigms: density maps and point regression. Given the field's security ramifications, there is active interest in model robustness against adversarial…

Transfer learning from pretrained language models recently became the dominant approach for solving many NLP tasks. A common approach to transfer learning for multiple tasks that maximize parameter sharing trains one or more task-specific…

Transfer-based attacks pose a significant threat to real-world applications by directly targeting victim models with adversarial examples generated on surrogate models. While numerous approaches have been proposed to enhance adversarial…

Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-trained cross-modal…

Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false…

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…

Autonomous vehicles (AVs) are more vulnerable to network attacks due to the high connectivity and diverse communication modes between vehicles and external networks. Deep learning-based Intrusion detection, an effective method for detecting…

Advanced Persistent Threats (APTs) are difficult to detect due to their complexity and stealthiness. To mitigate such attacks, many approaches model entities and their relationship using provenance graphs to detect the stealthy and…

In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attackers can carefully curate input strings that mislead LLMs…

Adversarial patch attacks can fool the face recognition (FR) models via small patches. However, previous adversarial patch attacks often result in unnatural patterns that are easily noticeable. Generating transferable and stealthy…

Large vision-language models (LVLMs) have shown remarkable capabilities in interpreting visual content. While existing works demonstrate these models' vulnerability to deliberately placed adversarial texts, such texts are often easily…

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the effectiveness of personalization techniques has lead to…

Written language contains stylistic cues that can be exploited to automatically infer a variety of potentially sensitive author information. Adversarial stylometry intends to attack such models by rewriting an author's text. Our research…

Adversarial attacks, particularly \textbf{targeted} transfer-based attacks, can be used to assess the adversarial robustness of large visual-language models (VLMs), allowing for a more thorough examination of potential security flaws before…

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by…

Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples. While existing methods typically achieve targeted attacks by aligning global features-such as CLIP's [CLS] token-between adversarial and target…