Related papers: Introducing Accountability to Anonymity Networks
Anonymous data collection systems allow users to contribute the data necessary to build services and applications while preserving their privacy. Anonymity, however, can be abused by malicious agents aiming to subvert or to sabotage the…
Deep Neural Networks (DNNs), as valuable intellectual property, face unauthorized use. Existing protections, such as digital watermarking, are largely passive; they provide only post-hoc ownership verification and cannot actively prevent…
This paper concerns the problem of the absence of ingress filtering at the network edge, one of the main causes of important network security issues. Numerous network operators do not deploy the best current practice - Source Address…
Provenance is an increasing concern due to the ongoing revolution in sharing and processing scientific data on the Web and in other computer systems. It is proposed that many computer systems will need to become provenance-aware in order to…
Stream-based communication dominates today's Internet, posing unique challenges for anonymous communication networks (ACNs). Traditionally designed for independent messages, ACNs struggle to account for the inherent vulnerabilities of…
In mobile ad hoc networks, by attacking the corresponding routing protocol, an attacker can easily disturb the operations of the network. For ad hoc networks, till now many secured routing protocols have been proposed which contains some…
This paper presents FAIR, a forwarding accountability mechanism that incentivizes ISPs to apply stricter security policies to their customers. The Autonomous System (AS) of the receiver specifies a traffic profile that the sender AS must…
Cryptocurrency off-chain networks such as Lightning (e.g., Bitcoin) or Raiden (e.g., Ethereum) aim to increase the scalability of traditional on-chain transactions. To support nodes in learning about possible paths to route their…
The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones. In this paper, we propose a novel backdoor…
Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited…
Reverse engineering of a communications network is the process of identifying the communications protocol used in the network. This problem arises in various situations such as eavesdropping, intelligent jamming, cognitive radio, and…
The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during model deployment and can evade detection by conventional…
In the rapidly evolving landscape of communication and network security, the increasing reliance on deep neural networks (DNNs) and cloud services for data processing presents a significant vulnerability: the potential for backdoors that…
When individuals are subject to adverse outcomes from machine learning models, providing a recourse path to help achieve a positive outcome is desirable. Recent work has shown that counterfactual explanations - which can be used as a means…
Secure communication between two nodes in a network depends on reliable key management systems that generate and distribute keys between communicating nodes and a secure routing protocol that establishes a route between them. But due to…
Deep neural networks for image classification are well-known to be vulnerable to adversarial attacks. One such attack that has garnered recent attention is the adversarial backdoor attack, which has demonstrated the capability to perform…
Data provenance analysis has been used as an assistive measure for ensuring system integrity. However, such techniques are typically reactive approaches to identify the root cause of an attack in its aftermath. This is in part due to fact…
The modern Internet is highly dependent on trust communicated via certificates. However, in some cases, certificates become untrusted, and it is necessary to revoke them. In practice, the problem of secure revocation is still open.…
Shared, dynamic network infrastructures, such as dual-use LEO satellite constellations, pose critical threats to metadata privacy, particularly for state actors operating in mixed-trust environments. This work proposes an enhanced anonymity…
The paper studies how to release data about a critical infrastructure network (e.g., the power network or a transportation network) without disclosing sensitive information that can be exploited by malevolent agents, while preserving the…