Related papers: Assessing the Effectiveness of Binary-Level CFI Te…

Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…

Understanding how cognitive biases influence adversarial decision-making is essential for developing effective cyber defenses. Capture-the-Flag (CTF) competitions provide an ecologically valid testbed to study attacker behavior at scale,…

Binary decompilation plays a vital role in various cybersecurity and software engineering tasks. Recently, end-to-end decompilation methods powered by large language models (LLMs) have garnered significant attention due to their ability to…

Code Language Models (CLMs) have achieved tremendous progress in source code understanding and generation, leading to a significant increase in research interests focused on applying CLMs to real-world software engineering tasks in recent…

We empirically evaluate whether AI systems are more effective at attacking or defending in cybersecurity. Using CAI (Cybersecurity AI)'s parallel execution framework, we deployed autonomous agents in 23 Attack/Defense CTF battlegrounds.…

Reachability analysis is a fundamental program analysis with a wide variety of applications. We present FlowCFL, a framework for type-based reachability analysis in the presence of mutable data. Interestingly, the underlying semantics of…

Cyber-attacks continue to grow, both in terms of volume and sophistication. This is aided by an increase in available computational power, expanding attack surfaces, and advancements in the human understanding of how to make attacks…

Vulnerability prediction is valuable in identifying security issues efficiently, even though it requires the source code of the target software system, which is a restrictive hypothesis. This paper presents an experimental study to predict…

Model Inversion attacks aim to reconstruct information from private training data by exploiting access to a target model. Nearly all recent MI studies evaluate attack success using a standard framework that computes attack accuracy through…

Cybersecurity training has become a crucial part of computer science education and industrial onboarding. Capture the Flag (CTF) competitions have emerged as a valuable, gamified approach for developing and refining the skills of…

Large language models (LLMs) are increasingly used to help security analysts manage the surge of cyber threats, automating tasks from vulnerability assessment to incident response. Yet in operational CTI workflows, reliability gaps remain…

Binary code similarity analysis (BCSA) is widely used for diverse security applications, including plagiarism detection, software license violation detection, and vulnerability discovery. Despite the surging research interest in BCSA, it is…

Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs to bypass model safety mechanisms by encoding harmful…

Despite the popularity of feature importance (FI) measures in interpretable machine learning, the statistical adequacy of these methods is rarely discussed. From a statistical perspective, a major distinction is between analyzing a…

Smart contracts are frequently vulnerable to control-flow attacks based on confused deputies, reentrancy, and incorrect error handling. These attacks exploit the complexity of interactions among multiple possibly unknown contracts. Existing…

Quantitative theories of information flow give us an approach to relax the absolute confidentiality properties that are difficult to satisfy for many practical programs. The classical information-theoretic approaches for sequential…

Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier. Recent works showed that this approach yields an unfair classifier if the training set is corrupted. In this work, we study the…

In this work we investigate the problem of simultaneous privacy and integrity protection in cryptographic circuits. We consider a white-box scenario with a powerful, yet limited attacker. A concise metric for the level of probing and fault…

Following the increasing trends of malicious applications or cyber threats in general, program analysis has become a ubiquitous technique in extracting relevant features. The current state-of-the-art solutions seem to fall behind new…

Malware authors are continuously evolving their code base to include counter-analysis methods that can significantly hinder their detection and blocking. While the execution of malware in a sandboxed environment may provide a lot of…