Related papers: Transferable Adversarial Attacks on SAM and Its Do…

Breakthroughs in unsupervised domain adaptation (uDA) can help in adapting models from a label-rich source domain to unlabeled target domains. Despite these advancements, there is a lack of research on how uDA algorithms, particularly those…

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Generalization and robustness are both key desiderata for designing machine learning methods. Adversarial training can enhance robustness, but past work often finds it hurts generalization. In natural language processing (NLP), pre-training…

Adversarial Missingness (AM) attacks aim to manipulate model fitting by carefully engineering a missing data problem to achieve a specific malicious objective. AM attacks are significantly different from prior data poisoning attacks in that…

Adversarial attacks pose a significant threat to deep learning models, particularly in safety-critical applications like healthcare and autonomous driving. Recently, patch based attacks have demonstrated effectiveness in real-time inference…

Adversarial attacks exploiting unrestricted natural perturbations present severe security risks to deep learning systems, yet their transferability across models remains limited due to distribution mismatches between generated adversarial…

Despite providing high-performance solutions for computer vision tasks, the deep neural network (DNN) model has been proved to be extremely vulnerable to adversarial attacks. Current defense mainly focuses on the known attacks, but the…

DNN is presenting human-level performance for many complex intelligent tasks in real-world applications. However, it also introduces ever-increasing security concerns. For example, the emerging adversarial attacks indicate that even very…

Language-conditioned robotic learning has significantly enhanced robot adaptability by enabling a single model to execute diverse tasks in response to verbal commands. Despite these advancements, security vulnerabilities within this domain…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Deep neural network-based image classification can be misled by adversarial examples with small and quasi-imperceptible perturbations. Furthermore, the adversarial examples created on one classification model can also fool another different…

The recent strides in artificial intelligence (AI) and machine learning (ML) have propelled the rise of TinyML, a paradigm enabling AI computations at the edge without dependence on cloud connections. While TinyML offers real-time data…

Deep learning-based time series models are being extensively utilized in engineering and manufacturing industries for process control and optimization, asset monitoring, diagnostic and predictive maintenance. These models have shown great…

Attributing APT (Advanced Persistent Threat) malware to their respective groups is crucial for threat intelligence and cybersecurity. However, APT adversaries often conceal their identities, rendering attribution inherently adversarial.…

Some recent works revealed that deep neural networks (DNNs) are vulnerable to so-called adversarial attacks where input examples are intentionally perturbed to fool DNNs. In this work, we revisit the DNN training process that includes…

Recent work on adversarial attack has shown that Projected Gradient Descent (PGD) Adversary is a universal first-order adversary, and the classifier adversarially trained by PGD is robust against a wide range of first-order attacks. It is…

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations carefully crafted to fool the targeted DNN, in both the non-targeted and targeted case. In the non-targeted case, the attacker simply aims to induce…

Recent work has proposed several efficient approaches for generating gradient-based adversarial perturbations on embeddings and proved that the model's performance and robustness can be improved when they are trained with these contaminated…

Adversarial training has been empirically proven to be one of the most effective and reliable defense methods against adversarial attacks. However, almost all existing studies about adversarial training are focused on balanced datasets,…

Model Inversion (MI) attacks aim to reconstruct privacy-sensitive training data from released models by utilizing output information, raising extensive concerns about the security of Deep Neural Networks (DNNs). Recent advances in…