相关论文: WFDefProxy: Modularly Implementing and Empirically…
Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In…
Device fingerprinting combined with Machine and Deep Learning (ML/DL) report promising performance when detecting cyberattacks targeting data managed by resource-constrained spectrum sensors. However, the amount of data needed to train…
Online services that desire to operate anonymously routinely host themselves as 'Hidden Services' in the Tor network. However, these services are frequently threatened by deanonymization attacks, whereby their IP address and location may be…
Open, unclassified research on secure autonomy is constrained by limited access to operational platforms, contested communications infrastructure, and representative adversarial test conditions. This paper presents a threat-oriented digital…
Modern Web APIs allow developers to provide extensively customized experiences for website visitors, but the richness of the device information they provide also make them vulnerable to being abused to construct browser fingerprints,…
Tor Onion Services are a way to host websites and other internet services anonymously. Onion Services are often used to bypass internet censorship and provide information services to users in oppressive regimes. This paper presents an…
In Internet of Things, where billions of devices with limited resources are communicating with each other, security has become a major stumbling block affecting the progress of this technology. Existing authentication schemes-based on…
We measure how effective Privacy Enhancing Technologies (PETs) are at protecting users from website fingerprinting. Our measurements use both experimental and observational methods. Experimental methods allow control, precision, and use on…
Federated Learning (FL) is a collaborative machine learning approach allowing participants to jointly train a model without having to share their private, potentially sensitive local datasets with others. Despite its benefits, FL is…
Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial…
The Tor anonymity network allows users such as political activists and those under repressive governments to protect their privacy when communicating over the internet. At the same time, Tor has been demonstrated to be vulnerable to several…
Tor provides anonymity online by routing traffic through encrypted tunnels, called circuits, over paths of anonymizing relays. To enable users to connect to their selected destination servers without waiting for the circuit to be build, the…
Owing to the meteoric rise in the usage of cryptocurrencies, there has been a widespread adaptation of traditional financial applications such as lending, borrowing, margin trading, and more, to the cryptocurrency realm. In some cases, the…
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…
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…
On-line privacy is of major public concern. Unfortunately, for the average consumer, there is no simple mechanism to browse the Internet privately on multiple devices. Most available Internet privacy mechanisms are either expensive, not…
The Tor anonymity network is difficult to measure because, if not done carefully, measurements could risk the privacy (and potentially the safety) of the network's users. Recent work has proposed the use of differential privacy and secure…
Research on backdoor attacks in Federated Learning (FL) has accelerated in recent years, with new attacks and defenses continually proposed in an escalating arms race. However, the evaluation of these methods remains neither standardized…
Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedded in HTML content or visual interfaces. Existing guard…
Phishing webpages are continuously polluting the Web. Plenty of countermeasures have been proposed and the most advanced techniques leverage machine-learning methods that infer whether a webpage is benign or not by inspecting its visual…