Related papers: Disentangled Safety Adapters Enable Efficient Guar…

In computer vision, traditional ensemble learning methods exhibit either a low training efficiency or the limited performance to enhance the reliability of deep neural networks. In this paper, we propose a lightweight, loss-function-free,…

Reasoning models have demonstrated remarkable capabilities in complex reasoning tasks. However, ensuring their safety against adversarial jailbreak prompts remains a critical challenge. Due to the covert and deceptive nature of such…

As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete deployment harms. In these settings, guardrail failures are no…

Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based unlearning methods suffer from issues such as high computational costs, hyperparameter…

Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant…

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway…

Safety alignment is an essential research topic for real-world AI applications. Despite the multifaceted nature of safety and trustworthiness in AI, current safety alignment methods often focus on a comprehensive notion of safety. By…

Guardian models play a crucial role in ensuring the safety and ethical behavior of user-facing AI applications by enforcing guardrails and detecting harmful content. While standard guardian models are limited to predefined, static harm…

Probabilistic security assessment and real-time dynamic security assessments (DSA) are promising to better handle the risks of system operations. The current methodologies of security assessments may require many time-domain simulations for…

Safety alignment is essential for building trustworthy artificial intelligence, yet it remains challenging to enhance model safety without degrading general performance. Current approaches require computationally expensive searches for the…

Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable…

Multimodal recommendation enhances accuracy by leveraging visual and textual signals, and its success largely depends on learning high-quality cross-modal representations. Recent advances in Large Vision-Language Models (LVLMs) offer…

Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models generate harmful responses when faced with malicious prompts.…

We introduce Embedded Safety-Aligned Intelligence (ESAI), a theoretical framework for multi-agent reinforcement learning that embeds alignment constraints directly into agents internal representations using differentiable internal alignment…

Safety alignment -- training large language models (LLMs) to refuse harmful requests while remaining helpful -- is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures,…

Despite remarkable achievements in artificial intelligence, the deployability of learning-enabled systems in high-stakes real-world environments still faces persistent challenges. For example, in safety-critical domains like autonomous…

A critical goal of autonomy and artificial intelligence is enabling autonomous robots to rapidly adapt in dynamic and uncertain environments. Classic adaptive control and safe control provide stability and safety guarantees but are limited…

The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the model provider. This approach lacks flexibility in the face…

Large language models (LLMs) have achieved remarkable success in diverse tasks, yet their safety alignment remains fragile during adaptation. Even when fine-tuning on benign data or with low-rank adaptation, pre-trained safety behaviors are…

Automatic Speech Recognition (ASR) for adults' speeches has made significant progress by employing deep neural network (DNN) models recently, but improvement in children's speech is still unsatisfactory due to children's speech's distinct…