Related papers: SandBlaster: Reversing the Apple Sandbox
Today, users can "lift-and-shift" unmodified applications into modern, VM-based Trusted Execution Environments (TEEs) in order to gain hardware-based security guarantees. However, TEEs do not protect applications against disk rollback…
Many efficient data structures use randomness, allowing them to improve upon deterministic ones. Usually, their efficiency and correctness are analyzed using probabilistic tools under the assumption that the inputs and queries are…
Providing security for information is highly critical in the current era with devices enabled with smart technology, where assuming a day without the internet is highly impossible. Fast internet at a cheaper price, not only made…
In many practical natural language applications, user data are highly sensitive, requiring anonymous uploads of text data from mobile devices to the cloud without user identifiers. However, the absence of user identifiers restricts the…
Microarchitectural side channels expose unprotected software to information leakage attacks where a software adversary is able to track runtime behavior of a benign process and steal secrets such as cryptographic keys. As suggested by…
Real-world datasets inevitably contain biases that arise from different sources or conditions during data collection. Consequently, such inconsistency itself acts as a confounding factor that disturbs the cluster analysis. Existing methods…
Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…
In recent years, the rise of machine learning (ML) in cybersecurity has brought new challenges, including the increasing threat of backdoor poisoning attacks on ML malware classifiers. For instance, adversaries could inject malicious…
Much software, whether beneficent or malevolent, is distributed only as binaries, sans source code. Absent source code, understanding binaries' behavior can be quite challenging, especially when compiled under higher levels of compiler…
Adversarial attacks pose a major threat to machine learning and to the systems that rely on it. In the cybersecurity domain, adversarial cyber-attack examples capable of evading detection are especially concerning. Nonetheless, an example…
System call filtering is a widely used security mechanism for protecting a shared OS kernel against untrusted user applications. However, existing system call filtering techniques either are too expensive due to the context switch overhead…
Machine-learning models have been recently used for detecting malicious Android applications, reporting impressive performances on benchmark datasets, even when trained only on features statically extracted from the application, such as…
Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a novel benchmark construction framework that "distills"…
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…
Thanks to the advance of technology, all kinds of applications are becoming more complete and capable of performing complex tasks that save much of our time. But to perform these tasks, applications require that some personal information…
Android OS is severely fragmented by API updates and device vendors' OS customization, creating a market condition where vastly different OS versions coexist. This gives rise to compatibility crash problems where Android apps crash on…
Network services are among the riskiest programs executed by production systems. Such services execute large quantities of complex code and process data from arbitrary and untrusted network sources, often with high levels of system…
Cybersecurity tools are increasingly automated with artificial intelligent (AI) capabilities to match the exponential scale of attacks, compensate for the relatively slower rate of training new cybersecurity talents, and improve of the…
In today's digital world, cyberbullying is a serious problem that can harm the mental and physical health of people who use social media. This paper explains just how serious cyberbullying is and how it really affects indi-viduals exposed…
Many recent works have proposed methods to train classifiers with local robustness properties, which can provably eliminate classes of evasion attacks for most inputs, but not all inputs. Since data distribution shift is very common in…