English
Related papers

Related papers: Self-Guard: Defending Large Reasoning Models via e…

200 papers

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias,…

Cryptography and Security · Computer Science 2024-06-21 Suriya Ganesh Ayyamperumal , Limin Ge

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…

Cryptography and Security · Computer Science 2025-02-06 Xunguang Wang , Daoyuan Wu , Zhenlan Ji , Zongjie Li , Pingchuan Ma , Shuai Wang , Yingjiu Li , Yang Liu , Ning Liu , Juergen Rahmel

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

Large Language Models (LLMs) excel in many NLP tasks but remain prone to hallucinations, limiting trust in real-world applications. We present HalluGuard, a 4B-parameter Small Reasoning Model (SRM) for mitigating hallucinations in…

Computation and Language · Computer Science 2025-10-02 Loris Bergeron , Ioana Buhnila , Jérôme François , Radu State

Large vision-language models (LVLMs) are vulnerable to harmful input compared to their language-only backbones. We investigated this vulnerability by exploring LVLMs internal dynamics, framing their inherent safety understanding in terms of…

Artificial Intelligence · Computer Science 2025-07-30 Wanying Wang , Zeyu Ma , Han Zheng , Xin Tan , Mingang Chen

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Artificial Intelligence · Computer Science 2025-02-18 Yingshui Tan , Yilei Jiang , Yanshi Li , Jiaheng Liu , Xingyuan Bu , Wenbo Su , Xiangyu Yue , Xiaoyong Zhu , Bo Zheng

Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilities unlock substantial practical value, they also introduce…

Cryptography and Security · Computer Science 2026-05-25 Zhe Liu , Zonghao Ying , Wenxin Zhang , Quanchen Zou , Deyue Zhang , Dongdong Yang , Xiangzheng Zhang , Hao Peng

Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as…

Machine Learning · Computer Science 2024-12-19 Hayder Elesedy , Pedro M. Esperança , Silviu Vlad Oprea , Mete Ozay

Reasoning-based language models have demonstrated strong performance across various domains, with the most notable gains seen in mathematical and coding tasks. Recent research has shown that reasoning also offers significant benefits for…

Artificial Intelligence · Computer Science 2025-05-27 Makesh Narsimhan Sreedhar , Traian Rebedea , Christopher Parisien

Large language models (LLMs) have transformed natural language processing (NLP), enabling applications from content generation to decision support. Retrieval-Augmented Generation (RAG) improves LLMs by incorporating external knowledge but…

Cryptography and Security · Computer Science 2025-11-11 Zirui Cheng , Jikai Sun , Anjun Gao , Yueyang Quan , Zhuqing Liu , Xiaohua Hu , Minghong Fang

Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed that LALMs remain vulnerable to harmful queries due to…

Computation and Language · Computer Science 2025-05-27 Hao Yang , Lizhen Qu , Ehsan Shareghi , Gholamreza Haffari

In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a…

Machine Learning · Computer Science 2024-11-01 Nabil Omi , Hosein Hasanbeig , Hiteshi Sharma , Sriram K. Rajamani , Siddhartha Sen

Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making…

Machine Learning · Computer Science 2026-02-13 Zhaoxin Wang , Jiaming Liang , Fengbin Zhu , Weixiang Zhao , Junfeng Fang , Jiayi Ji , Handing Wang , Tat-Seng Chua

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

Machine Learning · Computer Science 2026-05-05 Sadia Asif , Mohammad Mohammadi Amiri

LLM Agents are becoming central to intelligent systems. However, their deployment raises serious safety concerns. Existing defenses largely rely on "Safety Checks", which struggle to capture the complex semantic risks posed by harmful user…

Cryptography and Security · Computer Science 2025-09-16 Shiyu Xiang , Tong Zhang , Ronghao Chen

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) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

Computation and Language · Computer Science 2024-05-03 Mansi Phute , Alec Helbling , Matthew Hull , ShengYun Peng , Sebastian Szyller , Cory Cornelius , Duen Horng Chau

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…

Machine Learning · Computer Science 2026-03-17 Ming Wen , Kun Yang , Xin Chen , Jingyu Zhang , Dingding Han , Shiwen Cui , Yuedong Xu

Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative thinking. However, these models often exhibit overthinking (i.e.,…

Artificial Intelligence · Computer Science 2025-06-19 Weixiang Zhao , Jiahe Guo , Yang Deng , Xingyu Sui , Yulin Hu , Yanyan Zhao , Wanxiang Che , Bing Qin , Tat-Seng Chua , Ting Liu