Related papers: A Leak-Resilient Dual Stack Scheme for Backward-Ed…

Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly…

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Memory-unsafe programming languages such as C and C++ are the preferred languages for systems programming, embedded systems, and performance-critical applications. The widespread use of these languages makes the risk of memory-related…

Layer 2 systems have received increasing attention due to their potential to scale the throughput of L1 blockchains. To avoid the cost of putting data on chain, these systems increasingly turn to off-chain data availability solutions such…

This paper introduces a novel, fully distributed control framework for DC microgrids, enhancing resilience against exponentially unbounded false data injection (EU-FDI) attacks. Our framework features a consensus-based secondary control for…

This article conducts an extensive examination of the persisting challenges related to smart contract attacks within blockchain networks, with a particular focus on the reentrancy attack. It emphasizes the inherent vulnerabilities embedded…

Logic locking has emerged as a prominent key-driven technique to protect the integrity of integrated circuits. However, novel machine-learning-based attacks have recently been introduced to challenge the security foundations of locking…

Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Although evolving defense mechanisms can detect most existing…

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

This paper studies the distributed resilient output containment control of heterogeneous multiagent systems against composite attacks, including denial-of-services (DoS) attacks, false-data injection (FDI) attacks, camouflage attacks, and…

Data-Flow Integrity (DFI) is a well-known approach to effectively detecting a wide range of software attacks. However, its real-world application has been quite limited so far because of the prohibitive performance overhead it incurs.…

The rapid development of information and network technologies motivates the emergence of various new computing paradigms, such as distributed computing, and edge computing. This also enables more and more network enterprises to provide…

With the vigorous development of artificial intelligence technology, various engineering technology applications have been implemented one after another. The gradient descent method plays an important role in solving various optimization…

Rising device use and third-party IP integration in semiconductors raise security concerns. Unauthorized access, fault injection, and privacy invasion are potential threats from untrusted actors. Different security techniques have been…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation. These attacks pose great threats to the applications of…

Data deduplication is able to effectively identify and eliminate redundant data and only maintain a single copy of files and chunks. Hence, it is widely used in cloud storage systems to save storage space and network bandwidth. However, the…

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily focus on reducing latency and improving throughput through…

The proliferation of large language models for code (CodeLMs) and open-source contributions has heightened concerns over unauthorized use of source code datasets. While watermarking provides a viable protection mechanism by embedding…

A memory leak in an application deployed on the cloud can affect the availability and reliability of the application. Therefore, identifying and ultimately resolve it quickly is highly important. However, in the production environment…

Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning. However, prior work has centered around empirical observations of gradient inversion attacks, lacks theoretical grounding, and…