Related papers: Attacking Automatic Video Analysis Algorithms: A C…
Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…
The standard way of training video models entails sampling at each iteration a single clip from a video and optimizing the clip prediction with respect to the video-level label. We argue that a single clip may not have enough temporal…
Deep neural networks for video classification, just like image classification networks, may be subjected to adversarial manipulation. The main difference between image classifiers and video classifiers is that the latter usually use…
Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalizability across diverse downstream tasks. However, recent studies have revealed that VLMs, including CLIP, are highly vulnerable to adversarial…
Cyber security attacks have become increasingly complex over time, with various phases of their kill chain, involving binaries, scripts, documents, executed commands, vulnerabilities, or network traffic. We propose a tool, GView, that is…
The practicality of a video surveillance system is adversely limited by the amount of queries that can be placed on human resources and their vigilance in response. To transcend this limitation, a major effort under way is to include…
This paper describes the evolution of our research from video analytics to a global security system with focus on the video surveillance component. Indeed video surveillance has evolved from a commodity security tool up to the most…
We describe a protocol to study text-to-video retrieval training with unlabeled videos, where we assume (i) no access to labels for any videos, i.e., no access to the set of ground-truth captions, but (ii) access to labeled images in the…
With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the evasion attacks and the poisoning attacks attempt to utilize…
The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to…
In visible-infrared video person re-identification (re-ID), extracting features not affected by complex scenes (such as modality, camera views, pedestrian pose, background, etc.) changes, and mining and utilizing motion information are the…
Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations. In this paper, we propose another type of adversarial attack that can cheat classifiers by significant…
Deep neural networks for image classification are well-known to be vulnerable to adversarial attacks. One such attack that has garnered recent attention is the adversarial backdoor attack, which has demonstrated the capability to perform…
Adversarial attacks on machine learning models have seen increasing interest in the past years. By making only subtle changes to the input of a convolutional neural network, the output of the network can be swayed to output a completely…
Machine learning models are known to be vulnerable to adversarial attacks, but traditional attacks have mostly focused on single-modalities. With the rise of large multi-modal models (LMMs) like CLIP, which combine vision and language…
Machine learning algorithms are used to construct a mathematical model for a system based on training data. Such a model is capable of making highly accurate predictions without being explicitly programmed to do so. These techniques have a…
Adversarial perturbations can be added to images to protect their content from unwanted inferences. These perturbations may, however, be ineffective against classifiers that were not {seen} during the generation of the perturbation, or…
Deep neural networks have achieved great success for video analysis and understanding. However, designing a high-performance neural architecture requires substantial efforts and expertise. In this paper, we make the first attempt to let…
We study the problem of attacking video recognition models in the black-box setting, where the model information is unknown and the adversary can only make queries to detect the predicted top-1 class and its probability. Compared with the…
Deep learning classifiers are susceptible to well-crafted, imperceptible variations of their inputs, known as adversarial attacks. In this regard, the study of powerful attack models sheds light on the sources of vulnerability in these…