相关论文: Automated U.S Diplomatic Cables Security Classific…

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information…

Underground forums where users discuss, buy, and sell illicit services and goods facilitate a better understanding of the economy and organization of cybercriminals. Prior work has shown that in particular private interactions provide a…

Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to…

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…

Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014).…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when these exemplars contain sensitive information,…

Due to the variety of cyber-attacks or threats, the cybersecurity community enhances the traditional security control mechanisms to an advanced level so that automated tools can encounter potential security threats. Very recently, Cyber…

When AI agents retrieve and reason over external documents, adversaries can manipulate the data they receive to subvert their behaviour. Previous research has studied indirect prompt injection, where the attacker injects malicious…

In recent years, Deep Neural Networks (DNNs) have had a dramatic impact on a variety of problems that were long considered very difficult, e. g., image classification and automatic language translation to name just a few. The accuracy of…

Distributed machine learning has been widely used in recent years to tackle the large and complex dataset problem. Therewith, the security of distributed learning has also drawn increasing attentions from both academia and industry. In this…

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Federated learning is an established method for training machine learning models without sharing training data. However, recent work has shown that it cannot guarantee data privacy as shared gradients can still leak sensitive information.…

Data Distribution Service (DDS) is an innovative approach towards communication in ICS/IoT infrastructure and robotics. Being based on the cross-platform and cross-language API to be applicable in any computerised device, it offers the…

Phishing attacks are one of the trending cyber attacks that apply socially engineered messages that are communicated to people from professional hackers aiming at fooling users to reveal their sensitive information, the most popular…

The unchecked spread of digital information, combined with increasing political polarization and the tendency of individuals to isolate themselves from opposing political viewpoints, has driven researchers to develop systems for…

With the development of incipient technologies, user devices becoming more exposed and ill-used by foes. In upcoming decades, traditional security measures will not be sufficient enough to handle this huge threat towards distributed…

Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However,…

The increasing digitization of political speech has opened the door to studying a new dimension of political behavior using text analysis. This work investigates the value of word-level statistical data from the US Congressional…

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but pose risks of inadvertently exposing copyrighted or proprietary data, especially when such data is used for training but not intended for distribution.…