Related papers: Toward an Efficient Website Fingerprinting Defense

Nowadays, mobile smart devices are widely used in daily life. It is increasingly important to prevent malicious users from accessing private data, thus a secure and convenient authentication method is urgently needed. Compared with common…

Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information (PII) from public pages. Many prior defenses are deployed at…

Automated bots now account for roughly half of all web requests, and an increasing number deliberately spoof their identity to either evade detection or to not respect robots.txt. Existing countermeasures are either resource-intensive…

Automatic speech recognition systems have created exciting possibilities for applications, however they also enable opportunities for systematic eavesdropping. We propose a method to camouflage a person's voice over-the-air from these…

It is well known that when IoT traffic is unencrypted it is possible to identify the active devices based on their TCP/IP headers. And when traffic is encrypted, packet-sizes and timings can still be used to do so. To defend against such…

An unsolved challenge in distributed or federated learning is to effectively mitigate privacy risks without slowing down training or reducing accuracy. In this paper, we propose TextHide aiming at addressing this challenge for natural…

Recently, the membership inference attack poses a serious threat to the privacy of confidential training data of machine learning models. This paper proposes a novel adversarial example based privacy-preserving technique (AEPPT), which adds…

Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit endlessly many surface forms, making jailbreak mitigation…

In the problem of location anonymity of the events exposed to a global eavesdropper, we highlight and analyze some aspects that are missing in the prior work, which is especially relevant for the quality of secure sensing in…

Web-based behavior-manipulation attacks (BMAs) - such as scareware, fake software downloads, tech support scams, etc. - are a class of social engineering (SE) attacks that exploit human decision-making vulnerabilities. These attacks remain…

Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense's inner workings or approaches based on an ensemble of fixed attacks, none of which may…

While the rapid development of facial recognition algorithms has enabled numerous beneficial applications, their widespread deployment has raised significant concerns about the risks of mass surveillance and threats to individual privacy.…

Federated learning (FL) enables privacy-preserving model training by keeping data decentralized. However, it remains vulnerable to label-flipping attacks, where malicious clients manipulate labels to poison the global model. Despite their…

The apps installed on a smartphone can reveal much information about a user, such as their medical conditions, sexual orientation, or religious beliefs. Additionally, the presence or absence of particular apps on a smartphone can inform an…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Moving target defenses (MTD) are proactive security techniques that enhance network security by confusing the attacker and limiting their attack window. MTDs have been shown to have significant benefits when evaluated against traditional…

Website Fingerprinting (WF) attacks can effectively identify the websites visited by Tor clients via analyzing encrypted traffic patterns. Existing attacks focus on identifying different websites, but their accuracy dramatically decreases…

Denial of service attacks pose a threat in constant growth. This is mainly due to their tendency to gain in sophistication, ease of implementation, obfuscation and the recent improvements in occultation of fingerprints. On the other hand,…

Modern automated surveillance techniques are heavily reliant on deep learning methods. Despite the superior performance, these learning systems are inherently vulnerable to adversarial attacks - maliciously crafted inputs that are designed…

In this study, we investigate the protection offered by federated learning algorithms against eavesdropping adversaries. In our model, the adversary is capable of intercepting model updates transmitted from clients to the server, enabling…