相关论文: How Effective is Multiple-Vantage-Point Domain Con…

Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…

Face signatures, including size, shape, texture, skin tone, eye color, appearance, and scars/marks, are widely used as discriminative, biometric information for access control. Despite recent advancements in facial recognition systems,…

Vehicular Public Key Infrastructure (VPKI) plays a vital role in ensuring secure and privacy-preserving communication in vehicular ad hoc networks (VANETs). However, current VPKI architectures face significant challenges in terms of…

Hundreds of defenses have been proposed to make deep neural networks robust against minimal (adversarial) input perturbations. However, only a handful of these defenses held up their claims because correctly evaluating robustness is…

Real-time network verification promises to automatically detect violations of network-wide reachability invariants on the data plane. To be useful in practice, these violations need to be detected in the order of milliseconds, without…

The prosperity of deep neural networks (DNNs) is largely benefited from open-source datasets, based on which users can evaluate and improve their methods. In this paper, we revisit backdoor-based dataset ownership verification (DOV), which…

With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to unimodal domains but have expanded to more complex multimodal…

The wide deployment of deep neural networks, though achieving great success in many domains, has severe safety and reliability concerns. Existing adversarial attack generation and automatic verification techniques cannot formally verify…

As organizations increasingly use cloud services to host their IT infrastructure, there is a need to share data among these cloud hosted services and systems. A majority of IT organizations have workloads spread across different cloud…

Adversarial patch attacks threaten the reliability of modern vision models. We present PatchMap, the first spatially exhaustive benchmark of patch placement, built by evaluating over 1.5e8 forward passes on ImageNet validation images.…

A resilient multi-vehicle system cooperatively performs tasks by exchanging information, detecting, and removing cyber attacks that have the intent of hijacking or diminishing performance of the entire system. In this paper, we propose a…

Modern malware families often rely on domain-generation algorithms (DGAs) to determine rendezvous points to their command-and-control server. Traditional defence strategies (such as blacklisting domains or IP addresses) are inadequate…

Modern computing systems face security threats, including memory corruption attacks, speculative execution vulnerabilities, and control-flow hijacking. Although existing solutions address these threats individually, they frequently…

Poor security of Internet routing enables adversaries to divert user data through unintended infrastructures (hijack). Of particular concern -- and the focus of this paper -- are cases where attackers reroute domestic traffic through…

The central building block of secure and privacy-preserving Vehicular Communication (VC) systems is a Vehicular Public-Key Infrastructure (VPKI), which provides vehicles with multiple anonymized credentials, termed pseudonyms. These…

Graph Neural Networks (GNNs) have received significant attention due to their state-of-the-art performance on various graph representation learning tasks. However, recent studies reveal that GNNs are vulnerable to adversarial attacks, i.e.…

It is well-known that recurrent neural networks (RNNs), although widely used, are vulnerable to adversarial attacks including one-frame attacks and multi-frame attacks. Though a few certified defenses exist to provide guaranteed robustness…

Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. A victim classifier will predict to an attacker-desired target class whenever a test sample is embedded with the same backdoor pattern (BP) that was used to…

By leveraging the principle of software polyculture to ensure security in a network, we proposed a vulnerability-based software diversity metric to determine how a network topology can be adapted to minimize security vulnerability while…

Online government services are increasingly regarded as critical national infrastructure. Because these services directly influence public trust, any disruption can have significant societal and political consequences. Yet their supporting…