Search Results

This article departs from the conventional considerations of homogeneous and continuous structures to propose a master–slave heterogeneous frame of time-space discrete inertial neural networks with feedback control at the boundary. The aim of ...

Assessing the stealthiness of adversarial perturbations is challenging due to the lack of appropriate evaluation metrics. Existing evaluation metrics, e.g., <inline-formula> <tex-math notation="LaTeX">$L_{p}$ </tex-math></inline-formula> norms or Image ...

Modern Autonomous Vehicles (AVs) implement the Visual Perception Module (VPM) to perceive their surroundings. This VPM adopts various Deep Neural Network (DNN) models to process the data collected from cameras and LiDAR. Prior studies have shown that ...

Existing defense approaches against sensor spoofing attacks suffer from the limitations of limited specific attack types, requiring GPU computation, exhibiting considerable detection latency and struggling with the interpretability of corner cases. We ...

Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but they have also been observed to magnify societal biases, particularly those related to gender. In response to this issue, several benchmarks have been ...

Graph Transformer is a new architecture that surpasses GNNs in graph learning. While there emerge inspiring algorithm advancements, their practical adoption is still limited, particularly on real-world graphs involving up to millions of nodes. We observe ...

Cryptographic schemes like Fully Homomorphic Encryption (FHE) and Zero-Knowledge Proofs (ZKPs), while offering powerful privacy-preserving capabilities, are often hindered by their computational complexity. Polynomial multiplication, a core operation in ...

Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. In this paper, we consider a practical post-...

Text-to-image (T2I) diffusion models enjoy great popularity and many individuals and companies build their applications based on publicly released T2I diffusion models. Previous studies have demonstrated that backdoor attacks can elicit T2I diffusion ...

Instruction-driven image editing allows users to quickly edit an image according to text instructions in a forward pass. Nevertheless, malicious users can easily exploit this technique to create fake images, which could cause a crisis of trust and ...

Backdoor attack aims to induce neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems. Existing ...

Federated Learning (FL) suffers from severe performance degradation due to the data heterogeneity among clients. Some existing work suggests that the fundamental reason is that data heterogeneity can cause local model drift, and therefore proposes to ...

Time-lock puzzles (TLP) are a cryptographic tool that allow one to encrypt a message into the future, for a predetermined amount of time T. At present, we have only two constructions with provable security: One based on the repeated squaring ...

Circuit-based Private Set Intersection (circuit-PSI) empowers two parties, a client and a server, each with input sets X and Y, to securely compute a function f on the intersection X ∩ Y while preserving the confidentiality of X ∩ Y from both parties. ...

Zero-knowledge (ZK) proofs have been recently explored for the integrity of machine learning (ML) inference. However, these protocols suffer from high computational overhead, with the primary bottleneck stemming from the evaluation of non-linear ...

Penetration testing, a crucial industrial practice for ensuring system security, has traditionally resisted automation due to the extensive expertise required by human professionals. Large Language Models (LLMs) have shown significant advancements in ...

Circuits in deterministic decomposable negation normal form (d-DNNF) are representations of Boolean functions that enable linear-time model counting. This paper strengthens our theoretical knowledge of what classes of functions can be efficiently ...

Model quantization is a compression technique that converts a full-precision model to a more compact low-precision version for better storage. Despite the great success of quantization, recent studies revealed the feasibility of malicious exploiting ...

Diffusion models have achieved remarkable success in generating high-quality images. Recently, the open-source models represented by Stable Diffusion (SD) are thriving and are accessible for customization, giving rise to a vibrant community of creators ...

Natural language prompts serve as an essential interface between users and Large Language Models (LLMs) like GPT-3.5 and GPT-4, which are employed by ChatGPT to produce outputs across various tasks. However, prompts crafted with malicious intent, known ...