相关论文: An efficient structural attack on NIST submission …

Deep Neural Networks (DNNs) are widely acknowledged to be susceptible to adversarial examples, wherein imperceptible perturbations are added to clean examples through diverse input transformation attacks. However, these methods originally…

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…

Our work targets at searching feasible adversarial perturbation to attack a classifier with high-dimensional categorical inputs in a domain-agnostic setting. This is intrinsically an NP-hard knapsack problem where the exploration space…

Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on…

We consider the two-way quantum cryptographic protocol with coherent states assuming direct reconciliation. A detailed security analysis is performed considering a two-mode coherent attack, that represents the residual eavesdropping once…

In this paper we study the security of the key of compact McEliece schemes based on alternant/Goppa codes with a non-trivial permutation group, in particular quasi-cyclic alternant codes. We show that it is possible to reduce the…

Deformable Attention Transformers (DAT) have shown remarkable performance in computer vision tasks by adaptively focusing on informative image regions. However, their data-dependent sampling mechanism introduces irregular memory access…

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Machine learning systems based on deep neural networks (DNNs) have gained mainstream adoption in many applications. Recently, however, DNNs are shown to be vulnerable to adversarial example attacks with slight perturbations on the inputs.…

Quantized neural network (NN) with a reduced bit precision is an effective solution to reduces the computational and memory resource requirements and plays a vital role in machine learning. However, it is still challenging to avoid the…

Recently, Neural Architecture Search (NAS) methods are introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer (NAT) aims to improve the given neural architecture to have…

Motivated by the rise of quantum computers, existing public-key cryptosystems are expected to be replaced by post-quantum schemes in the next decade in billions of devices. To facilitate the transition, NIST is running a standardization…

The vulnerability of deep neural networks to adversarial examples has drawn tremendous attention from the community. Three approaches, optimizing standard objective functions, exploiting attention maps, and smoothing decision surfaces, are…

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.…

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…

In this paper, we propose a new key-based defense focusing on both efficiency and robustness. Although the previous key-based defense seems effective in defending against adversarial examples, carefully designed adaptive attacks can bypass…

Current Transferable Adversarial Examples (TAE) are primarily generated by adding Adversarial Noise (AN). Recent studies emphasize the importance of optimizing Data Augmentation (DA) parameters along with AN, which poses a greater threat to…

Inferring causal structure from data is a challenging task of fundamental importance in science. Observational data are often insufficient to identify a system's causal structure uniquely. While conducting interventions (i.e., experiments)…

Network coding-based link failure recovery techniques provide near-hitless recovery and offer high capacity efficiency. Diversity coding is the first technique to incorporate coding in this field and is easy to implement over small…

\textit{Differentiable ARchiTecture Search} (DARTS) has recently become the mainstream of neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-based bi-level optimization, DARTS alternately optimizes the…