Related papers: DynaGuard: A Dynamic Guardian Model With User-Defi…

As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

The growing accessibility of diffusion models has revolutionized image editing but also raised significant concerns about unauthorized modifications, such as misinformation and plagiarism. Existing countermeasures largely rely on…

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider…

Android is becoming ubiquitous and currently has the largest share of the mobile OS market with billions of application downloads from the official app market. It has also become the platform most targeted by mobile malware that are…

The rapid proliferation of AI-generated text online is profoundly reshaping the information landscape. Among various types of AI-generated text, AI-generated news presents a significant threat as it can be a prominent source of…

In the rapidly evolving landscape of communication and network security, the increasing reliance on deep neural networks (DNNs) and cloud services for data processing presents a significant vulnerability: the potential for backdoors that…

Large Language Models (LLMs) are prone to off-topic misuse, where users may prompt these models to perform tasks beyond their intended scope. Current guardrails, which often rely on curated examples or custom classifiers, suffer from high…

Cybersecurity is being fundamentally reshaped by foundation-model-based artificial intelligence. Large language models now enable autonomous planning, tool orchestration, and strategic adaptation at scale, challenging security architectures…

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrails, which filter the…

AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…

As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater.…

Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to traditional deep learning systems, there also exist potential…

This paper introduces BeaCon, a novel tool for the automated generation of adjustable container security policies. Unlike prior approaches, BeaCon leverages dynamic analysis to simulate realistic environments, uncovering container execution…

Artificial intelligence (AI) copilots are increasingly integrated into enterprise cybersecurity platforms to assist analysts in threat detection, triage, and remediation. However, the effectiveness of these systems depends not only on the…

The functionality of a deep learning (DL) model can be stolen via model extraction where an attacker obtains a surrogate model by utilizing the responses from a prediction API of the original model. In this work, we propose a novel…

This paper presents an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs). Focusing on both natural and code language tasks, we explore the vulnerabilities these…

Policy Cards are introduced as a machine-readable, deployment-layer standard for expressing operational, regulatory, and ethical constraints for AI agents. The Policy Card sits with the agent and enables it to follow required constraints at…

This paper presents the gatekeeper algorithm, a real-time and computationally-lightweight method that ensures that trajectories of a nonlinear system satisfy safety constraints despite sensing limitations. gatekeeper integrates with…

Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations that mislead deep learning models. While adversarial example detection offers a lightweight…