Related papers: SEA-Guard: Culturally Grounded Multilingual Safegu…
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.…
AI safety has emerged as a critical priority as these systems are increasingly deployed in real-world applications. We propose the first domain-agnostic AI safety ensuring framework that achieves strong safety guarantees while preserving…
With the widespread adoption of cryptocurrencies, cryptojacking has become a significant security threat to crypto wallet users. This paper presents a front-end prototype of an AI-powered security dashboard, namely, CryptoGuard. Developed…
Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction. The emergence of foundation models as the "brain" of EAI agents for high-level task planning has shown promising…
As large language models (LLMs) rapidly advance, their role in code generation has expanded significantly. While this offers streamlined development, it also creates concerns in areas like education and job interviews. Consequently,…
Various AI safety datasets have been developed to measure LLMs against evolving interpretations of harm. Our evaluation of five recently published open-source safety benchmarks reveals distinct semantic clusters using UMAP dimensionality…
Against rising global loneliness, AI companions promise connection, yet accumulating evidence suggests that, for some users and contexts, intensive companion-style use can correlate with increased loneliness and reduced offline…
The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…
The rapid development of autoregressive Large Language Models (LLMs) has significantly improved the quality of generated texts, necessitating reliable machine-generated text detectors. A huge number of detectors and collections with AI…
Securing Agentic Artificial Intelligence (AI) systems requires addressing the complex cyber risks introduced by autonomous, decision-making, and adaptive behaviors. Agentic AI systems are increasingly deployed across industries,…
AI agents that interact with their environments through tools enable powerful applications, but in high-stakes business settings, unintended actions can cause unacceptable harm, such as privacy breaches and financial loss. Existing…
Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…
Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models. Unfortunately, applying such models to settings with embodied…
Recent advances in AI-generated content have fueled the rise of highly realistic synthetic videos, posing severe risks to societal trust and digital integrity. Existing benchmarks for video authenticity detection typically suffer from…
This paper contributes to the nascent debate around safety cases for frontier AI systems. Safety cases are structured, defensible arguments that a system is acceptably safe to deploy in a given context. Historically, they have been used in…
The trend towards large language models (LLMs) for guardrailing against undesired behaviors is increasing and has shown promise for censoring user inputs. However, increased latency, memory consumption, hosting expenses and non-structured…
In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…
Cultural awareness in language models is the capacity to understand and adapt to diverse cultural contexts. However, most existing approaches treat culture as static background knowledge, overlooking its dynamic and evolving nature. This…
The challenge of language grounding is to fully understand natural language by grounding language in real-world referents. While AI techniques are available, the widespread adoption and effectiveness of such technologies for human-robot…
Modern software systems are increasingly developed within rapid continuous integration and deployment (CI/CD) pipelines, where ensuring security prior to release presents significant technical and organizational challenges. Traditional…