相关论文: NoSEBrEaK - Attacking Honeynets

We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural networks. In contrast to adversarial data modification,…

For many IT-security measures exact costs and benefits are not known. This makes it difficult to allocate resources optimally to different security measures. We present a model for costs and benefits of so called Honeynets. This can foster…

In the recent years, the fast development and the exponential utilization of social networks have prompted an expansion of social Computing. In social networks users are interconnected by edges or links, where Facebook, twitter, LinkedIn…

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Existing approaches to monitoring AI agents rely on supervised evaluation: human-written rules or LLM-based judges that check for known failure modes. However, novel misbehaviors may fall outside predefined categories entirely and LLM-based…

Attacks by Advanced Persistent Threats (APTs) have been shown to be difficult to detect using traditional signature- and anomaly-based intrusion detection approaches. Deception techniques such as decoy objects, often called honey items, may…

Advanced persistent threats (APTs) are stealthy attacks which make use of social engineering and deception to give adversaries insider access to networked systems. Against APTs, active defense technologies aim to create and exploit…

When the training data are maliciously tampered, the predictions of the acquired deep neural network (DNN) can be manipulated by an adversary known as the Trojan attack (or poisoning backdoor attack). The lack of robustness of DNNs against…

Defending against botnets has always been a cat and mouse game. Cyber-security researchers and government agencies attempt to detect and take down botnets by playing the role of the cat. In this context, a lot of work has been done towards…

HiveLink, the IoT-based Smart Bee Hive Monitoring System addresses the challenges faced by beekeepers in managing the influence of environmental impact, diseases, and collapse in honey bee colonies. Integrated with advanced sensors, the…

Decoy passwords, or "honeywords," planted in a credential database can alert a site to its breach if ever submitted in a login attempt. To be effective, some honeywords must appear at least as likely to be user-chosen passwords as the real…

Detection and location of moving prey utilizing electrosense or mechanosense is a strategy commonly followed by animals which cannot rely on visual sense or hearing. In this article we consider the possibility to detect the source of a…

We develop a decentralized $H_\infty$ synthesis approach to detection of biasing misappropriation attacks on distributed observers. Its starting point is to equip the observer with an attack model which is then used in the design of attack…

Mobile devices have widespread to become the most used piece of technology. Due to their characteristics, they have become major targets for botnet-related malware. FluBot is one example of botnet malware that infects mobile devices. In…

Triggerable watermarking enables model owners to assert ownership against model extraction attacks. However, most existing approaches require additional training, which limits post-deployment flexibility, and the lack of clear theoretical…

We present a novel methodology for neural network backdoor attacks. Unlike existing training-time attacks where the Trojaned network would respond to the Trojan trigger after training, our approach inserts a Trojan that will remain dormant…

A mobile ad hoc network (MANET) is a collection of mobile nodes that communicate with each other by forming a multi-hop radio network. Security remains a major challenge for these networks due to their features of open medium, dynamically…

Surveillance performance is studied for a wireless eavesdropping system, where a full-duplex legitimate monitor eavesdrops a suspicious link efficiently with the artificial noise (AN) assistance. Different from the existing work in the…

In this work we study the problem of misbehavior detection in wireless networks. A commonly adopted approach is to utilize the broadcasting nature of the wireless medium and have nodes monitor their neighborhood. We call such nodes the…

Simply restricting the computation to non-sensitive part of the data may lead to inferences on sensitive data through data dependencies. Inference control from data dependencies has been studied in the prior work. However, existing…