Related papers: LLM Safety From Within: Detecting Harmful Content …

Most prior safety research of large language models (LLMs) has focused on enhancing the alignment of LLMs to better suit the safety requirements of humans. However, internalizing such safeguard features into larger models brought challenges…

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In…

We present JavelinGuard, a suite of low-cost, high-performance model architectures designed for detecting malicious intent in Large Language Model (LLM) interactions, optimized specifically for production deployment. Recent advances in…

As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge. Ideally, LLMs should provide informative responses while avoiding the disclosure of harmful or…

The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak…

Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are…

We present ShieldGemma, a comprehensive suite of LLM-based safety content moderation models built upon Gemma2. These models provide robust, state-of-the-art predictions of safety risks across key harm types (sexually explicit, dangerous…

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…

As Large Language Models (LLMs) are increasingly deployed in safety-critical applications, robust content moderation becomes essential. We present a comprehensive evaluation of 14 open-source safety guard models on a curated benchmark of…

With the recent proliferation of large language models (LLMs), enterprises have been able to rapidly develop proof-of-concepts and prototypes. As a result, there is a growing need to implement robust guardrails that monitor, quantize and…

Large language models (LLMs) are widely used in real-world applications, raising concerns about their safety and trustworthiness. While red-teaming with jailbreak prompts exposes the vulnerabilities of LLMs, current efforts focus primarily…

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already…

Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making…

Insider threats pose a persistent and critical security risk, yet are notoriously difficult to detect in complex enterprise environments, where malicious actions are often hidden within seemingly benign user behaviors. Although…

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

Large language models (large LMs) are increasingly trained on massive codebases and used to generate code. However, LMs lack awareness of security and are found to frequently produce unsafe code. This work studies the security of LMs along…