相关论文: Safety Reasoning with Guidelines

Large reasoning models (LRMs) exhibit unprecedented capabilities in solving complex problems through Chain-of-Thought (CoT) reasoning. However, recent studies reveal that their final answers often contradict their own reasoning traces. We…

Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel…

Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution (OOD) inputs. This limitation is one of the key challenges in the adoption of deep learning models in high-assurance…

Adversarial training (AT) has been demonstrated as one of the most promising defense methods against various adversarial attacks. To our knowledge, existing AT-based methods usually train with the locally most adversarial perturbed points…

Reinforcement learning (RL) based post-training for explicit chain-of-thought (e.g., GRPO) improves the reasoning ability of multimodal large-scale reasoning models (MLRMs). But recent evidence shows that it can simultaneously degrade…

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

The rapid advancement of multi-modal large reasoning models (MLRMs) -- enhanced versions of multimodal language models (MLLMs) equipped with reasoning capabilities -- has revolutionized diverse applications. However, their safety…

Domain generalization aims to solve the challenge of Out-of-Distribution (OOD) generalization by leveraging common knowledge learned from multiple training domains to generalize to unseen test domains. To accurately evaluate the OOD…

Large Language Model (LLM) unlearning aims to erase or suppress undesirable knowledge within the model, offering promise for controlling harmful or private information to prevent misuse. However, recent studies highlight its limited…

Existing defenses against adversarial examples such as adversarial training typically assume that the adversary will conform to a specific or known threat model, such as $\ell_p$ perturbations within a fixed budget. In this paper, we focus…

Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests.…

There is increasing interest in data-driven approaches for recommending optimal treatment strategies in many chronic disease management and critical care applications. Reinforcement learning methods are well-suited to this sequential…

Reinforcement Learning (RL) has been shown to be effective in many scenarios. However, it typically requires the exploration of a sufficiently large number of state-action pairs, some of which may be unsafe. Consequently, its application to…

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock…

The reusability of state-of-the-art Pre-trained Language Models (PLMs) is often limited by their generalization problem, where their performance drastically decreases when evaluated on examples that differ from the training dataset, known…

Large language models (LLMs) have gained widespread recognition for their superior comprehension and have been deployed across numerous domains. Building on Chain-of-Thought (CoT) ideology, Large Reasoning models (LRMs) further exhibit…

Similar to other machine learning frameworks, Offline Reinforcement Learning (RL) is shown to be vulnerable to poisoning attacks, due to its reliance on externally sourced datasets, a vulnerability that is exacerbated by its sequential…

Numerous machine learning (ML) models have been developed, including those for software engineering (SE) tasks, under the assumption that training and testing data come from the same distribution. However, training and testing distributions…

We propose VulnLLM-R, the~\emph{first specialized reasoning LLM} for vulnerability detection. Our key insight is that LLMs can reason about program states and analyze the potential vulnerabilities, rather than simple pattern matching. This…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose many challenges for defense systems, including (1) adaptation…