相关论文: Low-Cost Hard-Label Adversarial Attack with Theore…

We propose the first general-purpose gradient-based attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix,…

Deep neural networks and other machine learning systems, despite being extremely powerful and able to make predictions with high accuracy, are vulnerable to adversarial attacks. We proposed the DeltaBound attack: a novel, powerful attack in…

While modern day web applications aim to create impact at the civilization level, they have become vulnerable to adversarial activity, where the next cyber-attack can take any shape and can originate from anywhere. The increasing scale and…

Machine learning models deployed as a service (MLaaS) are susceptible to model stealing attacks, where an adversary attempts to steal the model within a restricted access framework. While existing attacks demonstrate near-perfect…

Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models. In this paper, we…

In recent years, the adversarial vulnerability of deep neural networks (DNNs) has raised increasing attention. Among all the threat models, no-box attacks are the most practical but extremely challenging since they neither rely on any…

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

In the era of foundation models, CLIP has emerged as a powerful tool for aligning text & visual modalities into a common embedding space. However, the alignment objective used to train CLIP often results in subpar visual features for…

In the domain of backdoor attacks, accurate labeling of injected data is essential for evading rudimentary detection mechanisms. This imperative has catalyzed the development of clean-label attacks, which are notably more elusive as they…

Adversarial examples are known as carefully perturbed images fooling image classifiers. We propose a geometric framework to generate adversarial examples in one of the most challenging black-box settings where the adversary can only…

Adversarial machine learning is an emerging area showing the vulnerability of deep learning models. Exploring attack methods to challenge state of the art artificial intelligence (A.I.) models is an area of critical concern. The reliability…

We introduce a new black-box attack achieving state of the art performances. Our approach is based on a new objective function, borrowing ideas from $\ell_\infty$-white box attacks, and particularly designed to fit derivative-free…

Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a…

In the literature on adversarial examples, white box and black box attacks have received the most attention. The adversary is assumed to have either full (white) or no (black) access to the defender's model. In this work, we focus on the…

Widely used deep learning models are found to have poor robustness. Little noises can fool state-of-the-art models into making incorrect predictions. While there is a great deal of high-performance attack generation methods, most of them…

Previous studies have verified that the functionality of black-box models can be stolen with full probability outputs. However, under the more practical hard-label setting, we observe that existing methods suffer from catastrophic…

Semantic segmentation is a fundamental visual task that finds extensive deployment in applications with security-sensitive considerations. Nonetheless, recent work illustrates the adversarial vulnerability of semantic segmentation models to…

Backdoor poisoning attacks pose a well-known risk to neural networks. However, most studies have focused on lenient threat models. We introduce Silent Killer, a novel attack that operates in clean-label, black-box settings, uses a stealthy…

Image segmentation is an important problem in many safety-critical applications. Recent studies show that modern image segmentation models are vulnerable to adversarial perturbations, while existing attack methods mainly follow the idea of…

With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation. Previous 3D adversarial attackers either follow the…