相关论文: Trust The Typical

The rapid evolution of generative models has led to a continuous emergence of multimodal safety risks, exposing the limitations of existing defense methods. To address these challenges, we propose ProGuard, a vision-language proactive guard…

While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on externally enforced compliance, optimizing models to detect…

Adaptive traffic signal control (TSC) has demonstrated strong effectiveness in managing dynamic traffic flows. However, conventional methods often struggle when unforeseen traffic incidents occur (e.g., accidents and road maintenance),…

As Large Language Models (LLMs) become increasingly integrated into many technological ecosystems across various domains and industries, identifying which model is deployed or being interacted with is critical for the security and…

Large Language Models (LLMs) have achieved remarkable success but remain highly susceptible to jailbreak attacks, in which adversarial prompts coerce models into generating harmful, unethical, or policy-violating outputs. Such attacks pose…

Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning attacks, which can compromise safety alignment and lead to harmful outputs. Existing…

Laboratories are prone to severe injuries from minor unsafe actions, yet continuous safety monitoring -- beyond mandatory pre-lab safety training -- is limited by human availability. Vision language models (VLMs) offer promise for…

Large Language Diffusion Models (LLDMs) exhibit comparable performance to LLMs while offering distinct advantages in inference speed and mathematical reasoning tasks.The precise and rapid generation capabilities of LLDMs amplify concerns of…

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…

Safety hazard identification and prevention are the key elements of proactive safety management. Previous research has extensively explored the applications of computer vision to automatically identify hazards from image clips collected…

Large language models (LLMs) and small language models (SLMs) are being adopted at remarkable speed, although their safety still remains a serious concern. With the advent of multilingual S/LLMs, the question now becomes a matter of scale:…

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

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…

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in…

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…

Large language models (LLMs) have strong capabilities in solving diverse natural language processing tasks. However, the safety and security issues of LLM systems have become the major obstacle to their widespread application. Many studies…

Ensuring the reliability and safety of machine learning models in open-world deployment is a central challenge in AI safety. This thesis develops both algorithmic and theoretical foundations to address key reliability issues arising from…

Large language models (LLMs) have significantly transformed the landscape of Natural Language Processing (NLP). Their impact extends across a diverse spectrum of tasks, revolutionizing how we approach language understanding and generations.…

Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional components. However, existing safety attribution methods…