English
Related papers

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

200 papers

Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety…

Computation and Language · Computer Science 2025-05-29 Xiaofei Wen , Wenxuan Zhou , Wenjie Jacky Mo , Muhao Chen

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…

Computation and Language · Computer Science 2026-04-24 Yannis Belkhiter , Seshu Tirupathi , Giulio Zizzo , John D. Kelleher

Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning…

Artificial Intelligence · Computer Science 2025-04-02 Yu Cui , Bryan Hooi , Yujun Cai , Yiwei Wang

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…

Cryptography and Security · Computer Science 2026-01-29 Xianglin Yang , Gelei Deng , Jieming Shi , Tianwei Zhang , Jin Song Dong

As multimodal reasoning improves the overall capabilities of Large Vision Language Models (LVLMs), recent studies have begun to explore safety-oriented reasoning, aiming to enhance safety awareness by analyzing potential safety risks during…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Fenghua Weng , Chaochao Lu , Xia Hu , Wenqi Shao , Wenjie Wang

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

Computation and Language · Computer Science 2025-09-29 Yahan Yang , Soham Dan , Shuo Li , Dan Roth , Insup Lee

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…

Cryptography and Security · Computer Science 2026-05-04 Md. Mehedi Hasan , Sk Tanzir Mehedi , Ziaur Rahman , Rafid Mostafiz , Md. Abir Hossain

Large Language Models (LLMs) fine-tuned to align with human values often exhibit alignment drift, producing unsafe or policy-violating completions when exposed to adversarial prompts, decoding perturbations, or paraphrased jailbreaks. While…

Artificial Intelligence · Computer Science 2025-08-05 Amitava Das , Vinija Jain , Aman Chadha

Large Language Models (LLMs) often exhibit limited logical coherence, mapping premises to conclusions without adherence to explicit inference rules. We propose Proof-Carrying Reasoning with LLMs (PCRLLM), a framework that constrains…

Computation and Language · Computer Science 2025-11-12 Tangrui Li , Pei Wang , Hongzheng Wang Christian Hahm , Matteo Spatola , Justin Shi

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Cryptography and Security · Computer Science 2025-10-21 Zhengyue Zhao , Yingzi Ma , Somesh Jha , Marco Pavone , Patrick McDaniel , Chaowei Xiao

Large Reasoning Models (LRMs) have significantly advanced beyond traditional Large Language Models (LLMs) with their exceptional logical reasoning capabilities, yet these improvements introduce heightened safety risks. When subjected to…

Cryptography and Security · Computer Science 2025-06-04 Yang Yao , Xuan Tong , Ruofan Wang , Yixu Wang , Lujundong Li , Liang Liu , Yan Teng , Yingchun Wang

AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…

Cryptography and Security · Computer Science 2026-04-07 Khanh Linh Nguyen , Hoa Nghiem , Tu Tran

Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input representation, often overlooking the vulnerabilities…

Cryptography and Security · Computer Science 2026-03-11 Quanchen Zou , Moyang Chen , Zonghao Ying , Wenzhuo Xu , Yisong Xiao , Deyue Zhang , Dongdong Yang , Zhao Liu , Xiangzheng Zhang

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on…

Artificial Intelligence · Computer Science 2025-12-23 Qinglin Zeng , Jing Yang , Keze Wang

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…

Computation and Language · Computer Science 2025-01-23 Melissa Kazemi Rad , Huy Nghiem , Andy Luo , Sahil Wadhwa , Mohammad Sorower , Stephen Rawls

The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medical diagnostics, where opaque models can undermine trust.…

Cryptography and Security · Computer Science 2024-11-26 Songning Lai , Yu Huang , Jiayu Yang , Gaoxiang Huang , Wenshuo Chen , Yutao Yue

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…

Computation and Language · Computer Science 2026-04-08 Lihao Sun , Hang Dong , Bo Qiao , Qingwei Lin , Dongmei Zhang , Saravan Rajmohan

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models…

Computation and Language · Computer Science 2026-02-10 Thilo Hagendorff , Erik Derner , Nuria Oliver

Intelligent software systems powered by Large Language Models (LLMs) are increasingly deployed in critical sectors, raising concerns about their safety during runtime. Through an industry-academic collaboration when deploying an LLM-powered…

Software Engineering · Computer Science 2025-09-23 Rui Yang , Michael Fu , Chakkrit Tantithamthavorn , Chetan Arora , Gunel Gulmammadova , Joey Chua

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…

Cryptography and Security · Computer Science 2026-04-15 Jiawei Chen , Yang Yang , Chao Yu , Yu Tian , Zhi Cao , Xue Yang , Linghao Li , Hang Su , Zhaoxia Yin