Related papers: CIPHER: Cybersecurity Intelligent Penetration-test…

Penetration testing is essential for assessing and strengthening system security against real-world threats, yet traditional workflows remain highly manual, expertise-intensive, and difficult to scale. Although recent advances in Large…

Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (LLMs) in automating…

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

The field of integrated circuit (IC) design is highly specialized, presenting significant barriers to entry and research and development challenges. Although large language models (LLMs) have achieved remarkable success in various domains,…

EEG-based emotion recognition (EER) has gained significant attention due to its potential for understanding and analyzing human emotions. While recent advancements in deep learning techniques have substantially improved EER, the field lacks…

Computer network defense is a partnership between automated systems and human cyber security analysts. The system behaviors, for example raising a high proportion of false alarms, likely impact cyber analyst performance. Experimentation in…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Collaborative Qualitative Analysis (CQA) can enhance qualitative analysis rigor and depth by incorporating varied viewpoints. Nevertheless, ensuring a rigorous CQA procedure itself can be both demanding and costly. To lower this bar, we…

Large Language Models (LLMs) are redefining offensive cybersecurity by allowing the generation of harmful machine code with minimal human intervention. While attackers take advantage of dark LLMs such as XXXGPT and WolfGPT to produce…

The prospect of artificial intelligence (AI) competing in the adversarial landscape of cyber security has long been considered one of the most impactful, challenging, and potentially dangerous applications of AI. Here, we demonstrate a new…

Public leaderboards increasingly suggest that large language models (LLMs) surpass human experts on benchmarks spanning academic knowledge, law, and programming. Yet most benchmarks are fully public, their questions widely mirrored across…

Zipr is a tool for static binary rewriting, first published in 2016. Zipr was engineered to support arbitrary program modification with an emphasis on low overhead, robustness, and flexibility to perform security enhancements and…

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models (LLMs) offer promising capabilities for enhancing threat…

As the frequency of cyber threats increases, conventional penetration testing is failing to capture the entirety of todays complex environments. To solve this problem, we propose the Vulnerability Mitigation System (VMS), a novel agent…

Improving software performance is an important yet challenging part of the software development cycle. Today, the majority of performance inefficiencies are identified and patched by performance experts. Recent advancements in deep learning…

Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adversarial attacks remain poorly understood. We present a systematic benchmark of…

Software plays a crucial role in our daily lives, and therefore the quality and security of software systems have become increasingly important. However, vulnerabilities in software still pose a significant threat, as they can have serious…

Current cybersecurity research increasingly acknowledges the human factor, yet remains fragmented, often treating user vulnerabilities as isolated and static traits. This paper introduces MORPHEUS, a holistic framework that operationalizes…

We present CAISAR, an open-source platform under active development for the characterization of AI systems' robustness and safety. CAISAR provides a unified entry point for defining verification problems by using WhyML, the mature and…

The advent of Federated Learning (FL) as a distributed machine learning paradigm has introduced new cybersecurity challenges, notably adversarial attacks that threaten model integrity and participant privacy. This study proposes an…