Related papers: TraceGuard: Process-Guided Firewall against Reason…

Large Reasoning Models (LRMs) have significantly enhanced their capabilities in complex problem-solving by introducing a thinking draft that enables multi-path Chain-of-Thought explorations before producing final answers. Ensuring the…

Jailbreak prompts are a practical and evolving threat to large language models (LLMs), particularly in agentic systems that execute tools over untrusted content. Many attacks exploit long-context hiding, semantic camouflage, and lightweight…

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

Evaluations of large language models (LLMs) primarily emphasize convergent logical reasoning, where success is defined by producing a single correct proof. However, many real-world reasoning problems admit multiple valid derivations,…

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…

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…

Large Language Models (LLMs) have transformed task automation and content generation across various domains while incorporating safety filters to prevent misuse. We introduce a novel jailbreaking framework that employs distributed prompt…

Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks on LLM reasoning are constrained by specific settings or…

Despite their superior performance on a wide range of domains, large language models (LLMs) remain vulnerable to misuse for generating harmful content, a risk that has been further amplified by various jailbreak attacks. Existing jailbreak…

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning…

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…

Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat each problem in isolation and do not systematically reuse knowledge from prior reasoning…

While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation…

Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. However, the continual learning aspect of these aligned LLMs has been largely overlooked. Existing…

Large Reasoning Models (LRMs) have achieved tremendous success with their chain-of-thought (CoT) reasoning, yet also face safety issues similar to those of basic language models. In particular, while algorithms are designed to guide them to…

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), as it reflects their ability to derive valid conclusions from given premises. While the combination of test-time scaling with…

Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for detecting jailbreak prompts are primarily online moderation APIs or finetuned LLMs. These strategies, however, often require extensive and…

Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning, significantly improving mathematical and logical problem solving. However, this explicit reasoning process also introduces…