English
Related papers

Related papers: StructBreak: Structural Cognitive Overload-Induced…

200 papers

Large language models (LLMs) for code generation are typically evaluated on functional correctness alone, overlooking whether generated code propagates harmful content embedded in the prompt. Prior work has shown that most Code LLMs…

Software Engineering · Computer Science 2026-04-15 Honghao Tan , Haibo Wang , Shin Hwei Tan

The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and…

Cryptography and Security · Computer Science 2026-01-05 Haoran Gu , Handing Wang , Yi Mei , Mengjie Zhang , Yaochu Jin

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Cryptography and Security · Computer Science 2026-04-03 Nanxi Li , Zhengyue Zhao , G. Edward Suh , Marco Pavone , Chaowei Xiao

Recent advances in test-time scaling have enabled Large Language Models (LLMs) to display sophisticated reasoning abilities via extended Chain-of-Thought (CoT) generation. Despite their potential, these Reasoning LLMs (RLMs) often…

Computation and Language · Computer Science 2025-05-21 Zhen Xiong , Yujun Cai , Zhecheng Li , Yiwei Wang

Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…

Cryptography and Security · Computer Science 2026-04-17 Zhengxian Wu , Juan Wen , Wanli Peng , Haowei Chang , Yinghan Zhou , Yiming Xue

Chain-of-thought (CoT) has emerged as a critical mechanism for enhancing reasoning capabilities in large language models (LLMs), with self-consistency demonstrating notable promise in boosting performance. However, inherent linguistic…

Computation and Language · Computer Science 2025-04-03 Zhiwei Yu , Tuo Li , Changhong Wang , Hui Chen , Lang Zhou

Unified Multimodal understanding and generation Models (UMMs) have demonstrated remarkable capabilities in both understanding and generation tasks. However, we identify a vulnerability arising from the generation-understanding coupling in…

Artificial Intelligence · Computer Science 2025-10-01 Shaoxiong Guo , Tianyi Du , Lijun Li , Yuyao Wu , Jie Li , Jing Shao

Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Yunhao Gou , Kai Chen , Zhili Liu , Lanqing Hong , Hang Xu , Zhenguo Li , Dit-Yan Yeung , James T. Kwok , Yu Zhang

Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…

Computation and Language · Computer Science 2025-10-28 Havva Alizadeh Noughabi , Julien Serbanescu , Fattane Zarrinkalam , Ali Dehghantanha

Large Language Models (LLMs) have revolutionized artificial intelligence (AI), driving breakthroughs in natural language understanding, text generation, and autonomous systems. However, the rapid growth of LLMs presents significant…

Software Engineering · Computer Science 2025-04-30 Yanzhe Hu , Shenao Wang , Tianyuan Nie , Yanjie Zhao , Haoyu Wang

Recent Large Language Models (LLMs) have significantly advanced natural language processing and automated decision-making. However, these models still encounter difficulties when performing complex reasoning tasks involving logical…

Computation and Language · Computer Science 2025-06-26 Yubo Dong , Hehe Fan

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Cryptography and Security · Computer Science 2026-04-30 Zheng-Xin Yong , Stephen H. Bach

Large language models (LLMs) are often constrained by rigid reasoning processes, limiting their ability to generate creative and diverse responses. To address this, a novel framework called LADDER is proposed, combining Chain-of-Thought…

Computation and Language · Computer Science 2025-06-17 Xintong Tang , Meiru Zhang , Shang Xiao , Junzhao Jin , Zihan Zhao , Liwei Li , Yang Zheng , Bangyi Wu

Solving topological grid puzzles requires reasoning over global spatial invariants such as connectivity, loop closure, and region symmetry and remains challenging for even the most powerful large language models (LLMs). To study these…

Artificial Intelligence · Computer Science 2026-03-13 Mayug Maniparambil , Nils Hoehing , Janak Kapuriya , Arjun Karuvally , Ellen Rushe , Anthony Ventresque , Noel O'Connor , Fergal Reid

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the…

Computation and Language · Computer Science 2025-06-30 Yichi Zhang , Siyuan Zhang , Yao Huang , Zeyu Xia , Zhengwei Fang , Xiao Yang , Ranjie Duan , Dong Yan , Yinpeng Dong , Jun Zhu

Large Language Models (LLMs) have been equipped with safety mechanisms to prevent harmful outputs, but these guardrails can often be bypassed through "jailbreak" prompts. This paper introduces a novel graph-based approach to systematically…

Cryptography and Security · Computer Science 2025-04-18 Sinan He , An Wang

Recent advances in Multi-Modal Large Language Models (MLLMs) have enabled unified processing of language, vision, and structured inputs, opening the door to complex tasks such as logical deduction, spatial reasoning, and scientific…

Artificial Intelligence · Computer Science 2025-07-03 Guiyao Tie , Xueyang Zhou , Tianhe Gu , Ruihang Zhang , Chaoran Hu , Sizhe Zhang , Mengqu Sun , Yan Zhang , Pan Zhou , Lichao Sun

Safety alignment is critical for the ethical deployment of large language models (LLMs), guiding them to avoid generating harmful or unethical content. Current alignment techniques, such as supervised fine-tuning and reinforcement learning…

Cryptography and Security · Computer Science 2026-03-27 Lichao Wu , Sasha Behrouzi , Mohamadreza Rostami , Maximilian Thang , Stjepan Picek , Ahmad-Reza Sadeghi

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…

Cryptography and Security · Computer Science 2026-04-22 Kun Wang , Cheng Qian , Miao Yu , Lilan Peng , Liang Lin , Jiaming Zhang , Tianyu Zhang , Yu Cheng , Yang Wang

In this paper, we study an emergent self-debiasing mechanisms against stereotypical content in Large Language Models (LLMs). Unlike traditional safety mechanisms that are primarily triggered by explicit input-level stimuli, self-debiasing…

Social and Information Networks · Computer Science 2026-05-12 Jingshen Zhang , Bo Wang , Yanlin Fu , Dongming Zhao , Ruifang He , Yuexian Hou , Zifei Yu
‹ Prev 1 8 9 10 Next ›