Related papers: TraceRouter: Robust Safety for Large Foundation Mo…

We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

Every call to an LLM classification endpoint produces a labeled input-output pair already retained in production logs. These pairs constitute a free, growing training set: a lightweight surrogate trained on them can absorb a significant…

Connected multi-agent robotic systems (MRS) are prone to deadlocks in an obstacle environment where the robots can get stuck away from their desired locations under a smooth low-level control policy. Without an external intervention, often…

Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. However, the decentralized nature of FL also opens vulnerabilities…

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…

Large language models (LLMs) often exhibit complementary strengths. Model routing harnesses these strengths by dynamically directing each query to the most suitable model, given a candidate model pool. However, routing performance relies on…

Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers craft prompts that bypass safety alignment and elicit unsafe responses. Among existing…

The widespread deployment of pre-trained language models (PLMs) has exposed them to textual backdoor attacks, particularly those planted during the pre-training stage. These attacks pose significant risks to high-reliability applications,…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness…

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…

The rapid proliferation of Large Language Models (LLMs) has led to a fragmented and inefficient ecosystem, a state of ``model lock-in'' where seamlessly integrating novel models remains a significant bottleneck. Current routing frameworks…

Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often isolate model behavior from the broader system context. This work introduces a goal-driven…

The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that…

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…

Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text editing. In this paper, we argue that existing evaluations…

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial…

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…

This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses functionally ordered, step-specific subspaces that become…