Related papers: BSEA-1 - A Stream Cipher Backdooring Technique

Manipulations of return addresses on the stack are the basis for a variety of attacks on programs written in memory unsafe languages. Dual stack schemes for protecting return addresses promise an efficient and effective defense against such…

Backdoor inversion, a central step in many backdoor defenses, is a reverse-engineering process to recover the hidden backdoor trigger inserted into a machine learning model. Existing approaches tackle this problem by searching for a…

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being proposed, successively or concurrently, in the status of a rapid arms…

As Large Language Models (LLMs) become increasingly integrated into software development workflows, they also become prime targets for adversarial attacks. Among these, backdoor attacks are a significant threat, allowing attackers to…

Hiding messages for countless security purposes has become a highly fascinating subject nowadays. Encryption facilitates the data hiding. With the express development of technology, people tend to figure out a method capable of hiding a…

Cyber attacks pose crucial threats to computer system security, and put digital treasuries at excessive risks. This leads to an urgent call for an effective intrusion detection system that can identify the intrusion attacks with high…

We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense falls within the category of post-development defenses that…

This paper discusses the application of known techniques, knowledge and technology in a novel way for encryption. Two distinct and separate methods are presented. Method 1: Alter the symbol set of the language by adding additional redundant…

The paper proposes a method to secure the Compressive Sensing (CS) streams. It consists in protecting part of the measurements by a secret key and inserting the code into the rest. The secret key is generated via a cryptographically secure…

Cryptography is vital for data security, but cryptographic algorithms can still be vulnerable to side-channel attacks (SCAs), physical assaults exploiting power consumption and EM radiation. SCAs pose a significant threat to cryptographic…

Advanced Encryption Standard (AES) algorithm is considered as a secured algorithm. Still, some security issues lie in the S-Box and the key used. In this paper, we have tried to give focus on the security of the key used. Here, the proposed…

In recent years many chaotic cryptosystems based on Baptista's seminal work have been proposed. We analyze the security of two of the newest and most interesting ones, which use a dynamically updated look-up table and also work as stream…

Cryptanalysis of knapsack cipher is a fascinating problem which has eluded the computing fraternity for decades. However, in most of the cases either the time complexity of the proposed algorithm is colossal or an insufficient number of…

Many streaming algorithms provide only a high-probability relative approximation. These two relaxations, of allowing approximation and randomization, seem necessary -- for many streaming problems, both relaxations must be employed…

Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive learning, MIM attains state-of-the-art performance by masking…

Biometric data, such as face images, are often associated with sensitive information (e.g medical, financial, personal government records). Hence, a data breach in a system storing such information can have devastating consequences. Deep…

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Intrusion detection into computer networks has become one of the most important issues in cybersecurity. Attackers keep on researching and coding to discover new vulnerabilities to penetrate information security system. In consequence…

Self-Supervised Learning (SSL) has emerged as a significant paradigm in representation learning thanks to its ability to learn without extensive labeled data, its strong generalization capabilities, and its potential for privacy…