相关论文: Improving Integrated Gradient-based Transferable A…

Malicious attackers can generate targeted adversarial examples by imposing tiny noises, forcing neural networks to produce specific incorrect outputs. With cross-model transferability, network models remain vulnerable even in black-box…

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-Instance Learning (MIL) is a recent machine learning paradigm which is immensely useful in various real-life applications, like image analysis, video anomaly detection, text classification, etc. It is well known that most of the…

Recent studies have revealed that modern image and video quality assessment (IQA/VQA) metrics are vulnerable to adversarial attacks. An attacker can manipulate a video through preprocessing to artificially increase its quality score…

Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…

An established way to improve the transferability of black-box evasion attacks is to craft the adversarial examples on an ensemble-based surrogate to increase diversity. We argue that transferability is fundamentally related to uncertainty.…

The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial…

Adversarial attacks present a significant security risk to image recognition tasks. Defending against these attacks in a real-life setting can be compared to the way antivirus software works, with a key consideration being how well the…

Adversarial examples (AE) with good transferability enable practical black-box attacks on diverse target models, where insider knowledge about the target models is not required. Previous methods often generate AE with no or very limited…

Deep neural networks (DNNs) are vulnerable to adversarial attack despite their tremendous success in many AI fields. Adversarial attack is a method that causes the intended misclassfication by adding imperceptible perturbations to…

The introduction of multimodal models is a huge step forward in Artificial Intelligence. A single model is trained to understand multiple modalities: text, image, video, and audio. Open-source multimodal models have made these breakthroughs…

Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which causes serious threats to security-critical applications. This motivated much research on providing mechanisms to make models more robust against adversarial attacks.…

Vision Transformers (ViTs) have been widely applied in various computer vision and vision-language tasks. To gain insights into their robustness in practical scenarios, transferable adversarial examples on ViTs have been extensively…

Adversarial examples are maliciously perturbed inputs designed to mislead machine learning (ML) models at test-time. They often transfer: the same adversarial example fools more than one model. In this work, we propose novel methods for…

Deep neural networks are susceptible to adversarial examples while suffering from incorrect predictions via imperceptible perturbations. Transfer-based attacks create adversarial examples for surrogate models and transfer these examples to…

Recent breakthroughs in defenses against adversarial examples, like adversarial training, make the neural networks robust against various classes of attackers (e.g., first-order gradient-based attacks). However, it is an open question…

Deep learning-based image denoising models demonstrate remarkable performance, but their lack of robustness analysis remains a significant concern. A major issue is that these models are susceptible to adversarial attacks, where small,…

Recent work has developed optimization procedures to find token sequences, called adversarial triggers, which can elicit unsafe responses from aligned language models. These triggers are believed to be highly transferable, i.e., a trigger…

Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better…

Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose…