English
Related papers

Related papers: Safety Context Injection: Inference-Time Safety Al…

200 papers

Ensuring and improving the safety of autonomous driving systems (ADS) is crucial for the deployment of highly automated vehicles, especially in safety-critical events. To address the rarity issue, adversarial scenario generation methods are…

Machine Learning · Computer Science 2025-06-10 Yuewen Mei , Tong Nie , Jian Sun , Ye Tian

The rapid advancement of large language models (LLMs) has demonstrated milestone success in a variety of tasks, yet their potential for generating harmful content has raised significant safety concerns. Existing safety evaluation approaches…

Computation and Language · Computer Science 2025-05-22 Tianqi Du , Zeming Wei , Quan Chen , Chenheng Zhang , Yisen Wang

Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs)…

Cryptography and Security · Computer Science 2025-06-06 Tiansheng Huang , Sihao Hu , Fatih Ilhan , Selim Furkan Tekin , Zachary Yahn , Yichang Xu , Ling Liu

The rapid emergence of new entities -- driven by cultural shifts, evolving trends, and personalized user data -- poses a significant challenge for existing Speech Large Language Models (Speech LLMs). While these models excel at general…

Artificial Intelligence · Computer Science 2026-02-06 Peidong Wang

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…

Computation and Language · Computer Science 2025-11-18 Xikang Yang , Biyu Zhou , Xuehai Tang , Jizhong Han , Songlin Hu

Large Reasoning Models (LRMs) have rapidly gained prominence for their strong performance in solving complex tasks. Many modern black-box LRMs expose the intermediate reasoning traces through APIs to improve transparency (e.g., Gemini-2.5…

Cryptography and Security · Computer Science 2026-01-21 Ruihan Hu , Yu-Ming Shang , Wei Luo , Ye Tao , Xi Zhang

Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent's performance while avoiding violations of safety…

Machine Learning · Computer Science 2021-01-05 Baiming Chen , Zuxin Liu , Jiacheng Zhu , Mengdi Xu , Wenhao Ding , Ding Zhao

Large Language Models (LLMs) struggle with long-horizon tasks due to the "context bottleneck" and the "lost-in-the-middle" phenomenon, where accumulated noise from verbose environments degrades reasoning over multi-turn interactions. To…

Artificial Intelligence · Computer Science 2026-04-14 Xiaozhe Li , Tianyi Lyu , Yizhao Yang , Liang Shan , Siyi Yang , Ligao Zhang , Zhuoyi Huang , Qingwen Liu , Yang Li

Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to…

Artificial Intelligence · Computer Science 2025-09-17 Wei Cai , Shujuan Liu , Jian Zhao , Ziyan Shi , Yusheng Zhao , Yuchen Yuan , Tianle Zhang , Chi Zhang , Xuelong Li

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Cryptography and Security · Computer Science 2026-03-03 Zhihang Deng , Jiaping Gui , Weinan Zhang

Large Language Models (LLMs) are increasingly vulnerable to Prompt Injection (PI) attacks, where adversarial instructions hidden within retrieved contexts hijack the model's execution flow. Current defenses typically face a critical…

Cryptography and Security · Computer Science 2026-02-03 Mingrui Liu , Sixiao Zhang , Cheng Long , Kwok-Yan Lam

This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on…

Artificial Intelligence · Computer Science 2025-08-11 Bo Wen

Long context reasoning in large language models (LLMs) has demonstrated enhancement of their cognitive capabilities via chain-of-thought (CoT) inference. Training such models is usually done via reinforcement learning with verifiable…

Computation and Language · Computer Science 2025-12-05 Purbesh Mitra , Sennur Ulukus

In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to unstable performance in classification. While calibration…

Machine Learning · Statistics 2026-03-05 Korel Gundem , Juncheng Dong , Dennis Zhang , Vahid Tarokh , Zhengling Qi

Large Language Models (LLMs) are increasingly deployed as agents that operate in real-world environments, introducing safety risks beyond linguistic harm. Existing agent safety evaluations rely on risk-oriented tasks tailored to specific…

Artificial Intelligence · Computer Science 2026-02-04 Jingnan Zheng , Yanzhen Luo , Jingjun Xu , Bingnan Liu , Yuxin Chen , Chenhang Cui , Gelei Deng , Chaochao Lu , Xiang Wang , An Zhang , Tat-Seng Chua

We propose a novel dynamic safety framework that optimizes language model (LM) safety reasoning at inference time without modifying model weights. Building on recent advances in self-critique methods, our approach leverages a meta-critique…

Computation and Language · Computer Science 2025-04-08 Víctor Gallego

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Cryptography and Security · Computer Science 2025-11-24 Yige Li , Zhe Li , Wei Zhao , Nay Myat Min , Hanxun Huang , Xingjun Ma , Jun Sun

Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develops a full-link security enhancement framework, which describes "input risk perception -…

Cryptography and Security · Computer Science 2026-05-12 Saisai Hu

Despite the promise of Retrieval-Augmented Generation in grounding Multimodal Large Language Models with external knowledge, the transition to extensive contexts often leads to significant attention dilution and reasoning hallucinations.…

Computation and Language · Computer Science 2026-03-10 Junming Liu , Yuqi Li , Shiping Wen , Zhigang Zeng , Tingwen Huang

The rise of Large Language Model (LLM) agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent…

Cryptography and Security · Computer Science 2026-05-06 Shihao Weng , Yang Feng , Jinrui Zhang , Xiaofei Xie , Jiongchi Yu , Jia Liu