Related papers: PIArena: A Platform for Prompt Injection Evaluatio…

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Smart homes, powered by programmable IoT platforms, often face safety and security issues. A class of defense solutions dynamically enforces policies that capture the expected behavior of the IoT system. Despite numerous innovations, these…

We present RapidPen, a fully automated penetration testing (pentesting) framework that addresses the challenge of achieving an initial foothold (IP-to-Shell) without human intervention. Unlike prior approaches that focus primarily on…

Prompt injection has emerged as a serious security threat to large language models (LLMs). At present, the current best-practice for defending against newly-discovered prompt injection techniques is to add additional guardrails to the…

Offensive security is one of the state of the art measures to protect enterprises and organizations. Penetration testing, broadly called pentesting, is a branch of offensive security designed to find, rate and exploit these vulnerabilities,…

The ability to rapidly adapt to novel and unforeseen environmental changes is a cornerstone of artificial general intelligence (AGI), yet it remains a critical blind spot in most existing AI benchmarks. Traditional evaluation largely…

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

Physically Unclonable Functions (PUFs) provide a streamlined solution for lightweight device authentication. Delay-based Arbiter PUFs, with their ease of implementation and vast challenge space, have received significant attention; however,…

The recent advances in reinforcement learning have led to effective methods able to obtain above human-level performances in very complex environments. However, once solved, these environments become less valuable, and new challenges with…

Large language models (LLMs) have been widely applied for their remarkable capability of content generation. However, the practical use of open-source LLMs is hindered by high resource requirements, making deployment expensive and limiting…

The field of defense strategies against adversarial attacks has significantly grown over the last years, but progress is hampered as the evaluation of adversarial defenses is often insufficient and thus gives a wrong impression of…

The integration of AI into modern critical infrastructure systems, such as healthcare, has introduced new vulnerabilities that can significantly impact workflow, efficiency, and safety. Additionally, the increased connectivity has made…

Real-Time systems are essential for promptly responding to external stimuli and completing tasks within predefined time constraints. Ensuring high reliability and robust security in these systems is therefore critical. This requires…

The integration of the Internet of Medical Things (IoMT) into healthcare systems has transformed patient care by enabling real-time monitoring, enhanced diagnostics, and enhanced operational efficiency. However, this increased connectivity…

Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being proposed, successively or concurrently, in the status of a rapid arms…

Advanced Persistent Threats (APTs) have created new security challenges for critical infrastructures due to their stealthy, dynamic, and adaptive natures. In this work, we aim to lay a game-theoretic foundation by establishing a multi-stage…

Embodied AI development significantly lags behind large foundation models due to three critical challenges: (1) lack of systematic understanding of core capabilities needed for Embodied AI, making research lack clear objectives; (2) absence…

In recent years, Deep Neural Networks (DNNs) have had a dramatic impact on a variety of problems that were long considered very difficult, e. g., image classification and automatic language translation to name just a few. The accuracy of…

Critical infrastructure increasingly relies on interconnected cyber-physical systems whose security incidents can escalate rapidly into safety and operational failures. Existing decision-support approaches struggle to support real-time…