Related papers: Take up DNSSEC When Needed

Recent research shows deep neural networks are vulnerable to different types of attacks, such as adversarial attack, data poisoning attack and backdoor attack. Among them, backdoor attack is the most cunning one and can occur in almost…

5G brings many improvements to cellular networks in terms of performance, such as lower latency, improved network efficiency, and higher throughput, making it an attractive candidate for many applications. One such domain is industrial…

DaemonSec is an early-stage startup exploring machine learning (ML)-based security for Linux daemons, a critical yet often overlooked attack surface. While daemon security remains underexplored, conventional defenses struggle against…

Machine learning techniques have been widely applied to various applications. However, they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can disrupt the learning procedure by injecting a fraction of…

Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

This paper proposes a defense scheme against malicious use of DNS tunnel. A tunnel validator is designed to provide trustworthy tunnel-aware defensive recursive service. In addition to the detection algorithm of malicious tunnel domains,…

Attacks on Internet routing are typically viewed through the lens of availability and confidentiality, assuming an adversary that either discards traffic or performs eavesdropping. Yet, a strategic adversary can use routing attacks to…

In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing…

Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic…

While storing documents on the cloud can be attractive, the question remains whether cloud providers can be trusted with storing private documents. Even if trusted, data breaches are ubiquitous. To prevent information leakage one can store…

Unencrypted DNS traffic between users and DNS resolvers can lead to privacy and security concerns. In response to these privacy risks, many browser vendors have deployed DNS-over-HTTPS (DoH) to encrypt queries between users and DNS…

Clustering algorithms have been increasingly adopted in security applications to spot dangerous or illicit activities. However, they have not been originally devised to deal with deliberate attack attempts that may aim to subvert the…

SDN promises to make networks more flexible, programmable, and easier to manage. Inherent security problems in SDN today, however, pose a threat to the promised benefits. First, the network operator lacks tools to proactively ensure that…

Caching content at the edge network is a popular and effective technique widely deployed to alleviate the burden of network backhaul, shorten service delay and improve service quality. However, there has been some controversy over privacy…

The benefits of the ubiquitous caching in ICN are profound, such features make ICN promising for content distribution, but it also introduces a challenge to content protection against the unauthorized access. The protection of a content…

Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they in general do not provide any guarantees, leaving them…

The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data poisoning, necessitating the study of robustness of learning algorithms against such attacks. Existing…

Data poisoning is a threat model in which a malicious actor tampers with training data to manipulate outcomes at inference time. A variety of defenses against this threat model have been proposed, but each suffers from at least one of the…

Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect…