Related papers: Bielik Guard: Efficient Polish Language Safety Cla…
Understanding how large language models (LLMs) process emotionally sensitive content is critical for building safe and reliable systems, particularly in mental health contexts. We investigate the scaling behavior of LLMs on two key tasks:…
Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios,…
Studying the robustness of Large Language Models (LLMs) to unsafe behaviors is an important topic of research today. Building safety classification models or guard models, which are fine-tuned models for input/output safety classification…
Large Language Models (LLMs) can generate content spanning ideological rhetoric to explicit instructions for violence. However, existing safety evaluations often rely on simplistic binary labels (safe and unsafe), overlooking the nuanced…
This paper examines the efficacy of utilizing large language models (LLMs) to detect public threats posted online. Amid rising concerns over the spread of threatening rhetoric and advance notices of violence, automated content analysis…
Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…
Large language models (LLMs) are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets. To address this gap, we present CyberPal 2.0, a family of…
Large Language Model (LLM) safety guardrail models have emerged as a primary defense mechanism against harmful content generation, yet their robustness against sophisticated adversarial attacks remains poorly characterized. This study…
Ensuring safe, policy-compliant outputs from large language models requires real-time content moderation that can scale across multiple safety dimensions. However, state-of-the-art guardrail models rely on autoregressive decoders with…
Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be deemed harmful.Efforts to mitigate this risk include…
Sensitive information detection is crucial in content moderation to maintain safe online communities. Assisting in this traditionally manual process could relieve human moderators from overwhelming and tedious tasks, allowing them to focus…
Since the Internet is flooded with hate, it is one of the main tasks for NLP experts to master automated online content moderation. However, advancements in this field require improved access to publicly available accurate and non-synthetic…
Large language models (LLMs) excel in text understanding and generation but raise significant safety and ethical concerns in high-stakes applications. To mitigate these risks, we present Libra-Guard, a cutting-edge safeguard system designed…
Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak attempts, and unsafe responses without the cost profile of large guardrail models, and…
We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful content and screen adversarial prompts in human-AI conversational settings. The first component,…
The proliferation of software vulnerabilities presents a significant challenge to cybersecurity, necessitating more effective detection methodologies. We introduce White-Basilisk, a novel approach to vulnerability detection that…
Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…
Powered by remarkable advancements in Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities in manifold tasks. However, the practical application scenarios of MLLMs are intricate,…
Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…
When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…