Related papers: Devil is Virtual: Reversing Virtual Inheritance in…

Binary code analysis plays an essential role in cybersecurity, facilitating reverse engineering to reveal the inner workings of programs in the absence of source code. Traditional approaches, such as static and dynamic analysis, extract…

Adversarial attacks present a significant security risk to image recognition tasks. Defending against these attacks in a real-life setting can be compared to the way antivirus software works, with a key consideration being how well the…

This paper presents an easy-to-use open-source software library for continuous-variable quantum key distribution (CV-QKD) systems. The library, written in C++, simplifies the crucial task of information reconciliation, ensuring that both…

Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the training…

Vision Transformers (ViTs) have demonstrated impressive performance across a range of applications, including many safety-critical tasks. However, their unique architectural properties raise new challenges and opportunities in adversarial…

Quantum trajectory methods can be used for a wide range of open quantum systems to solve the master equation by unraveling the density operator evolution into individual stochastic trajectories in Hilbert space. This C++ class library…

An Air Force evaluation of Multics, and Ken Thompson's famous Turing award lecture "Reflections on Trusting Trust," showed that compilers can be subverted to insert malicious Trojan horses into critical software, including themselves. If…

Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversary-specified labels while maintaining performance on clean…

Due to the increasing usage of machine learning (ML) techniques in security- and safety-critical domains, such as autonomous systems and medical diagnosis, ensuring correct behavior of ML systems, especially for different corner cases, is…

Motivated by the transformative impact of deep neural networks (DNNs) in various domains, researchers and anti-virus vendors have proposed DNNs for malware detection from raw bytes that do not require manual feature engineering. In this…

We constructed a newly large-scale and comprehensive C/C++ vulnerability dataset named MegaVul by crawling the Common Vulnerabilities and Exposures (CVE) database and CVE-related open-source projects. Specifically, we collected all…

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…

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with…

Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white…

The April 2026 Claude Mythos sandbox escape exposed a critical weakness in frontier AI containment: the infrastructure surrounding advanced models remains susceptible to formally characterizable arithmetic vulnerabilities. Anthropic has not…

Memory corruption vulnerabilities remain one of the most severe threats to software security. They often allow attackers to achieve arbitrary code execution by redirecting a vulnerable program's control flow. While Control Flow Integrity…

Low-level programming languages with weak/static type systems, such as C and C++, are vulnerable to errors relating to the misuse of memory at runtime, such as (sub-)object bounds overflows, (re)use-after-free, and type confusion. Such…

Reproducible builds are a set of software development practices that establish an independently verifiable path from source code to binary artifacts, helping to detect and mitigate certain classes of supply chain attacks. Although quantum…

Obfuscation is the action of making something unintelligible. In software development, this action can be applied to source code or binary applications. The aim of this dissertation was to implement a tool for the obfuscation of C and C++…

The advent of multimodal deep learning models, such as CLIP, has unlocked new frontiers in a wide range of applications, from image-text understanding to classification tasks. However, these models are not safe for adversarial attacks,…