Related papers: Mathematical Backdoors in Symmetric Encryption Sys…

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…

With the advent of quantum computing, and other advancements in computation and processing capabilities of modern systems, there arises a need to develop new trapdoor functions that will serve as the foundation for a new generation of…

Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited…

Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on…

Many security and software testing applications require checking whether certain properties of a program hold for any possible usage scenario. For instance, a tool for identifying software vulnerabilities may need to rule out the existence…

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…

With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect. We believe that answers to these…

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…

The goal of an algorithm substitution attack (ASA), also called a subversion attack (SA), is to replace an honest implementation of a cryptographic tool by a subverted one which allows to leak private information while generating output…

Today, the protection of information, ensuring of the safety and the recall in lossless in case of need is highly significant and it is seen as a major threat in the field. Information security is possible by hiding the available data, by…

Large language models (LLMs) have demonstrated powerful capabilities in both text understanding and generation. Companies have begun to offer Embedding as a Service (EaaS) based on these LLMs, which can benefit various natural language…

The ability to hide information from unauthorized individuals has been a prevalent issue over the years. Countless algorithms such as DES, AES and SHA have been developed. These algorithms depend on varying key length and key management…

Security issues are the most challenging problems in cloud computing environments as an emerging technology. Regarding to this importance, an efficient and reliable user authentication and data protection model has been presented in this…

Homomorphic encryption (HE) is a privacy-preserving technique that enables computation directly over ciphertext. Unfortunately, a key challenge for HE is that implementations can be impractically slow and have limits on computation that can…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Self-supervised learning in computer vision aims to pre-train an image encoder using a large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can then be used as a feature extractor to build downstream…

Backdoor attacks on language models pose a significant threat to AI safety, where models behave normally on most inputs but exhibit harmful behavior when triggered by specific patterns. Detecting such backdoors through mechanistic…

Traditional cryptography is facing great challenges with the development of quantum computing. Not only public-key cryptography, the applications of quantum algorithms to symmetric cryptanalysis has also drawn more and more attention. In…

Self-supervised learning in computer vision trains on unlabeled data, such as images or (image, text) pairs, to obtain an image encoder that learns high-quality embeddings for input data. Emerging backdoor attacks towards encoders expose…

Recently, a chaotic image encryption algorithm based on information entropy (IEAIE) was proposed. This paper scrutinizes the security properties of the algorithm and evaluates the validity of the used quantifiable security metrics. When the…