Related papers: Memory Efficient Full-gradient Attacks (MEFA) Fram…

Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…

Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples and achieve state-of-the-art robustness. Recent studies show that even advanced attacks cannot break such defenses…

Adversarial training and adversarial purification are two widely used defense strategies for enhancing model robustness against adversarial attacks. However, adversarial training requires costly retraining, while adversarial purification…

The vulnerability of deep networks to adversarial attacks is a central problem for deep learning from the perspective of both cognition and security. The current most successful defense method is to train a classifier using adversarial…

Deep neural networks are known to be vulnerable to adversarial perturbations, which are small and carefully crafted inputs that lead to incorrect predictions. In this paper, we propose DeepDefense, a novel defense framework that applies…

Adversarial attacks persist as a major challenge in deep learning. While training- and test-time defenses are well-studied, they often reduce clean accuracy, incur high cost, or fail under adaptive threats. In contrast, preemptive defenses,…

Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model's architecture and parameters. Traditional defense…

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…

We propose a new defense mechanism against adversarial attacks inspired by an optical co-processor, providing robustness without compromising natural accuracy in both white-box and black-box settings. This hardware co-processor performs a…

Diffusion-based purification (DBP) has become a cornerstone defense against adversarial examples (AEs), regarded as robust due to its use of diffusion models (DMs) that project AEs onto the natural data manifold. We refute this core claim,…

We question the current evaluation practice on diffusion-based purification methods. Diffusion-based purification methods aim to remove adversarial effects from an input data point at test time. The approach gains increasing attention as an…

LiDAR-based segmentation is essential for reliable perception in autonomous vehicles, yet modern segmentation networks are highly susceptible to adversarial attacks that can compromise safety. Most existing defenses are designed for…

Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box…

Recently, the area of adversarial attacks on image quality metrics has begun to be explored, whereas the area of defences remains under-researched. In this study, we aim to cover that case and check the transferability of adversarial…

Backdoor attacks pose a significant threat to deep neural networks, particularly as recent advancements have led to increasingly subtle implantation, making the defense more challenging. Existing defense mechanisms typically rely on an…

Deep neural networks are susceptible to small-but-specific adversarial perturbations capable of deceiving the network. This vulnerability can lead to potentially harmful consequences in security-critical applications. To address this…

The emergence of deep learning models has revolutionized various industries over the last decade, leading to a surge in connected devices and infrastructures. However, these models can be tricked into making incorrect predictions with high…

Adversarial attacks on deep learning models have compromised their performance considerably. As remedies, a lot of defense methods were proposed, which however, have been circumvented by newer attacking strategies. In the midst of this…

Machine learning-based malware detection is known to be vulnerable to adversarial evasion attacks. The state-of-the-art is that there are no effective defenses against these attacks. As a response to the adversarial malware classification…

Face authentication systems have brought significant convenience and advanced developments, yet they have become unreliable due to their sensitivity to inconspicuous perturbations, such as adversarial attacks. Existing defenses often…