Related papers: Automated Attack Planning
While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…
Discovering vulnerabilities in applications of real-world complexity is a daunting task: a vulnerability may affect a single line of code, and yet it compromises the security of the entire application. Even worse, vulnerabilities may…
Network systems often contain vulnerabilities that remain unfixed in a network for various reasons, such as the lack of a patch or knowledge to fix them. With the presence of such residual vulnerabilities, the network administrator should…
In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time; e.g., malware code is typically obfuscated using random strings or byte sequences to…
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…
Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…
Many of the core disciplines of artificial intelligence have sets of standard benchmark problems well known and widely used by the community when developing new algorithms. Constraint programming and automated planning are examples of these…
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…
We consider the problem of tracking an intruder using a network of wireless sensors. For tracking the intruder at each instant, the optimal number and the right configuration of sensors has to be powered. As powering the sensors consumes…
We introduce a method for Intrusion Detection based on the classification, understanding and prediction of behavioural deviance and potential threats, issuing recommendations, and acting to address eminent issues. Our work seeks a practical…
Applications that use Large Language Models (LLMs) are becoming widespread, making the identification of system vulnerabilities increasingly important. Automated Red Teaming accelerates this effort by using an LLM to generate and execute…
Penetration testing (PT) is an efficient network testing and vulnerability mining tool by simulating a hacker's attack for valuable information applied in some areas. Compared with manual PT, intelligent PT has become a dominating…
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the…
Fault Injection is the study of observing how systems behave under unusual stress, environmental or otherwise. In practice, fault injection involves testing the limits of computer systems and finding novel ways to potentially break…
Cybersecurity planning supports the selection of and implementation of security controls in resource-constrained settings to manage risk. Doing so requires considering adaptive adversaries with different levels of strategic sophistication…
Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…
Hypothesis testing is an important problem with applications in target localization, clinical trials etc. Many active hypothesis testing strategies operate in two phases: an exploration phase and a verification phase. In the exploration…
As the number of cyberattacks and their particualr nature escalate, the need for effective intrusion detection systems (IDS) has become indispensable for ensuring the security of contemporary networks. Adaptive and more sophisticated…
The rapid development and expansion of World Wide Web and network systems have changed the computing world in the last decade and also equipped the intruders and hackers with new facilities for their destructive purposes. The cost of…
Active classification, i.e., the sequential decision-making process aimed at data acquisition for classification purposes, arises naturally in many applications, including medical diagnosis, intrusion detection, and object tracking. In this…