相关论文: Hiding Behind Backdoors: Self-Obfuscation Against …

Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect…

Machine learning (ML) models that learn and predict properties of computer programs are increasingly being adopted and deployed. These models have demonstrated success in applications such as auto-completing code, summarizing large…

As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…

We consider the problem of obfuscating sensitive information while preserving utility, and we propose a machine learning approach inspired by the generative adversarial networks paradigm. The idea is to set up two nets: the generator, that…

While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…

Generative models such as GANs and diffusion models are widely used to synthesize photorealistic images and to support downstream creative and editing tasks. While adversarial attacks on discriminative models are well studied, attacks…

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…

Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…

In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…

Federated learning allows for clients in a distributed system to jointly train a machine learning model. However, clients' models are vulnerable to attacks during the training and testing phases. In this paper, we address the issue of…

Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poisoned test-time data while maintaining high clean accuracy in…

Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While…

Deep learning models have been deployed in numerous real-world applications such as autonomous driving and surveillance. However, these models are vulnerable in adversarial environments. Backdoor attack is emerging as a severe security…

Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in the form of backdoors during training. The goal of a backdoor is to corrupt the performance of the trained model on specific sub-tasks (e.g., by…

Backdoor learning has become an emerging research area towards building a trustworthy machine learning system. While a lot of works have studied the hidden danger of backdoor attacks in image or text classification, there is a limited…

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a…

The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…

Federated learning enables multiple clients to collaboratively contribute to the learning of a global model orchestrated by a central server. This learning scheme promotes clients' data privacy and requires reduced communication overheads.…

Autonomous vehicles, including self driving cars, ground robots, and drones, rely on multi-modal sensor pipelines for safe operation, yet remain vulnerable to adversarial sensor attacks. A critical gap is the lack of a systematic end-to-end…

Since there are multiple parties in collaborative learning, malicious parties might manipulate the learning process for their own purposes through backdoor attacks. However, most of existing works only consider the federated learning…