Related papers: An algebraic attack on stream ciphers with applica…
This paper deals with the merger of the two lightweight stream ciphers: A5by1 and Trivium. The idea is to make the key stream generation more secure and to remove the attacks of the individual algorithms. The bits generated by the Trivium…
The ability to accurately predict cyber-attacks would enable organizations to mitigate their growing threat and avert the financial losses and disruptions they cause. But how predictable are cyber-attacks? Researchers have attempted to…
The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these models. These attacks, which manipulate an LLM's output by…
A plethora of jailbreaking attacks have been proposed to obtain harmful responses from safety-tuned LLMs. These methods largely succeed in coercing the target output in their original settings, but their attacks vary substantially in…
Here we introduce an improved approach to Variational Quantum Attack Algorithms (VQAA) on crytographic protocols. Our methods provide robust quantum attacks to well-known cryptographic algorithms, more efficiently and with remarkably fewer…
Graph Neural Networks (GNNs) have become widely used in the field of graph mining. However, these networks are vulnerable to structural perturbations. While many research efforts have focused on analyzing vulnerability through poisoning…
This work tackles a critical challenge in AI safety research under limited compute: given a fixed computation budget, how can one maximize the strength of iterative adversarial attacks? Coarsely reducing the number of attack iterations…
Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input $x$ and any target classification $t$, it is possible to find a new…
Graph Neural Networks (GNNs) are highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods attempt to address this issue by filtering attacked graphs. However, they struggle…
The Alternating Step(r,s) Generator, ASG(r,s), is a clock-controlled sequence generator which is recently proposed by A. Kanso. It consists of three registers of length l, m and n bits. The first register controls the clocking of the two…
This paper concerns the analysis of information leaks in security systems. We address the problem of specifying and analyzing large systems in the (standard) channel model used in quantitative information flow (QIF). We propose several…
Graph neural networks have been widely utilized to solve graph-related tasks because of their strong learning power in utilizing the local information of neighbors. However, recent studies on graph adversarial attacks have proven that…
Unimodal maps have been broadly used as a base of new encryption strategies. Recently, a stream cipher has been proposed in the literature, whose keystream is basically a symbolic sequence of the (one-parameter) logistic map or of the tent…
Lightweight cryptographic primitives are widely deployed in resource-constrained environments, particularly in Internet of Things (IoT) devices. Due to their public accessibility, these devices are vulnerable to physical attacks, especially…
Large Language Models (LLMs) are increasingly integrated with graph-structured data for tasks like node classification, a domain traditionally dominated by Graph Neural Networks (GNNs). While this integration leverages rich relational…
Federated Learning (FL) is a novel client-server distributed learning framework that can protect data privacy. However, recent works show that FL is vulnerable to poisoning attacks. Many defenses with robust aggregators (AGRs) are proposed…
Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) by grounding their responses in structured knowledge graphs. Leveraging community detection and relation filtering…
Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text editing. In this paper, we argue that existing evaluations…
As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms designed to filter malicious queries while being easy to implement and update. In this…
Cryptographic primitives such as stream ciphers,Pseudorandom Number Generators (PRNGs), and block cipher modes produce sequences that are designed to be statistically indistinguishable from random data. As a result, the traditional…